ACL 2026 — LLMs & Foundation Models | Rajat Kanti Bhattacharjee

LLMs & Foundation Models

985 papers Links not yet available — ACL proceedings pending on ACL Anthology.

Your Inference Request Will Become a Black Box: Confidential Inference for Cloud-based Large Language Models
Rhetorical Questions in LLM Representations: A Linear Probing Study
Different types of syntactic agreement recruit the same units within large language models
Benchmarking LLM’s Capability in Reasoning over Conflicting Web References
Parallel Universes, Parallel Languages: A Comprehensive Study on LLM-based Multilingual Counterfactual Example Generation
Can Continual Pretraining Bridge the Performance Gap between General-purpose and Specialized Language Models in the Medical Domain?
MINTQA: A Multi-Hop Question Answering Benchmark for Evaluating LLMs on New and Long-tail Knowledge
PR-XAI: PageRank-Based Feature Attribution for Transformers
CAPruner: Conceptual-Adjacent Scene Graph Pruner for Enhancing 3D Spatial Reasoning of Large Language Models
Your Reasoning Model Knows What Counts: Self-Guided Chain-of-Thought Pruning for Efficient Reasoning
How Memory Management Impacts LLM Agents: An Empirical Study of Experience-Following Behavior
SACTOR: LLM-Driven Correct and Idiomatic C to Rust Translation with Static Analysis and FFI-Based Verification
IntrAgent: An LLM Agent for Content-Grounded Information Retrieval through Literature Review
Reasoning over Precedents Alongside Statutes: Case-Augmented Deliberative Alignment for LLM Safety
Augur: Modeling Covariate Causal Associations in Time Series via Large Language Models
AgentRouter: A Knowledge-Graph-Guided LLM Router for Collaborative Multi-Agent Question Answering
MoCa: Modality-aware Continual Pre-training Makes Better Bidirectional Multimodal Embeddings
DecIF: Improving Instruction-Following through Decomposition
NavA³: Understanding Any Instruction, Navigating Anywhere, Finding Anything
MemSearch-o1: Empowering Large Language Models with Reasoning-Aligned Memory Growth in Agentic Search
CAPC-CG: A Large-Scale, Expert-Directed LLM-Annotated Corpus of Adaptive Policy Communication in China
MathFlow: Enhancing the Perceptual Flow of MLLMs for Visual Mathematical Problems
What Makes Good Instruction-Tuning Data? An In-Context Learning Perspective
XtraGPT: Context-Aware and Controllable Academic Paper Revision via Human-AI Collaboration
Learn to Relax with Large Language Models: Solving Constraint Optimization Problems via Bidirectional Coevolution
Focusing Condition: Inference-Time Self-Contrastive Steering Elicits Better Conditional Text Embeddings in LLMs
Exploring Attention Attractors in Large Language Models
SPAGBias: Uncovering and Tracing Structured Spatial Gender Bias in Large Language Models
CoreGaze: Core Subgraph-Driven Visual Gaze Diffusion for Training-Free Referring Multimodal Large Language Models
RespiraMFM: A Multimodal Foundation Model with Contrastive Audio-Language Alignment for Respiratory Disease Identification
Beyond Detection: Evaluating Fallacy Awareness of LLMs in Interactive Scenarios
Crosscoding Through Time: Tracking Emergence & Consolidation Of Linguistic Representations Throughout LLM Pretraining
On the Emergence and Test-Time Use of Structural Information in Large Language Models
SAGE: A Search-AuGmented Evaluation of Large Language Models on Free‑Form QA
CachePrune: Teaching LLMs What Not to Follow via KV-Cache Editing
Flip-Flop Consistency: Unsupervised Training for Robustness to Prompt Perturbations in LLMs
Leave My Images Alone: Preventing Multi-Modal Large Language Models from Analyzing Images via Visual Prompt Injection
Harnessing Negative Signals: Reinforcement Distillation from Teacher Data for LLM Reasoning
SFTMix: Elevating Language Model Instruction Tuning with Mixup Recipe
Psychological Steering in LLMs: An Evaluation of Effectiveness and Trustworthiness
Erasing Without Remembering: Implicit Knowledge Forgetting in Large Language Models
What is a protest anyway? Codebook conceptualization is still a first-order concern in LLM-era classification
Contextual Relevance and Adaptive Sampling for LLM-Based Document Reranking
Quantifying Aleatoric Uncertainty of In-Context Learning for Robust Measure of LLM Prediction Confidence
SATQuest: A Verifier for Logical Reasoning Evaluation and Reinforcement Fine-Tuning of LLMs
EquivPruner: Boosting Efficiency and Quality in LLM-Based Search via Action Pruning
From Data-Centric to Sample-Centric: Enhancing LLM Reasoning via Progressive Optimization
TeRA: Vector-based Random Tensor Network for High-Rank Adaptation of Large Language Models
MMCLIP: Cross-Modal Attention Masked Modelling for Medical Language-Image Pre-Training
LaMI: Augmenting Large Language Models via Late Multi-Image Fusion
Toward Secure Tuning: Mitigating Security Risks from Instruction Fine-Tuning
SDE-SQL: Enhancing Text-to-SQL Generation in Large Language Models via Self-Driven Exploration with SQL Probes
Thinking beyond the anthropomorphic paradigm benefits LLM research
LightReasoner: Can Small Language Models Teach Large Language Models Reasoning?
SCAN: Structured Capability Assessment and Navigation for LLMs
EMCEE: Improving Multilingual Capability of LLMs via Bridging Knowledge and Reasoning with Extracted Synthetic Multilingual Context
Can LLMs Learn to Map the World from Local Descriptions?
ALIGN: Word Association Learning for Cultural Alignment in Large Language Models
Bias Fitting to Mitigate Length Bias of Reward Model in RLHF
Beyond Examples: Towards Automated Thought-level In-Context Reasoning for Large Language Models
Two-Stage Regularization-Based Structured Pruning for LLMs
K-Merge: Online Continual Merging of Adapters for On-device Large Language Models
TRACE: Evaluating Execution Efficiency of LLM-Based Code Translation
It’s Not What You Say, It’s How You Say It: Evaluating LLM Responses to Expressions of Belief
Bridging Language and Items for Retrieval and Recommendation: Benchmarking LLMs as Semantic Encoders
Evolutionary Guided Decoding: Iterative Value Refinement for LLMs
KG-MuLQA: A Framework for KG-based Multi-Level QA Extraction and Long-Context LLM Evaluation
BracketRank: Large Language Model Document Ranking via Reasoning-based Competitive Elimination
Multi-component Causal Tracing in Large Language Models
Sparse Feature Coactivation Reveals Causal Semantic Modules in Large Language Models
TensorLens: End-to-End Transformer Analysis via High-Order Attention Tensors
OASIS: Online Sample Selection for Continual Instruction Tuning
Chunks as Arms: Multi-Armed Bandit-Guided Sampling for Long-Context LLM Preference Optimization
CODERL+: Improving Code Generation via Reinforcement with Execution Semantics Alignment
Compressing then Matching: An Efficient Pre-training Paradigm for Multimodal Embedding
LLM-XTM: Enhancing Cross-Lingual Topic Models with Large Language Models
From Factuality to Meta-Factivity: A Cognitive Blueprint for Trustworthy LLMs
From ID to LLM: Rethinking Representation Learning for Recommendation
DMHM: Density-aware Manifold Learning and Hybrid Mahalanobis Energy for LLMs-generated Text Detection
SOS-LoRA: Static Orthogonal-Subspace Low-Rank Adaptation with Fixed Multi-Scale Scaling
Adam’s Law: Textual Frequency Law on Large Language Models
Are Emotion and Rhetoric Neurons in LLM? Neuron Recognition and Adaptive Masking for Emotion-Rhetoric Prediction Steering
Towards Fine-Grained and Multi-Granular Contrastive Language-Speech Pre-training
Between a Rock and a Hard Place: The Tension Between Ethical Reasoning and Safety Alignment in LLMs
Deliberative Searcher: Improving LLM Reliability via Reinforcement Learning with Constraints
Thermometer of Thoughts: Enhancing LLM’s Exploration via Attention Temperature Modulation
Illusions of Confidence? Diagnosing LLM Truthfulness via Neighborhood Consistency
Scaling Beyond Context: A Survey of Multimodal Retrieval-Augmented Generation for Document Understanding
Open Schrödinger’s Closed Box: Identifying Retrieval Augmented Generation in API-Accessible Large Language Model Services
Timely Machine: Awareness of Time Makes Test-Time Scaling Agentic
Multi-Granularity Semantic Revision for Large Language Model Distillation
Instruction Data Selection via Answer Divergence
Interpretable Safety Alignment via SAE-Constructed Low-Rank Subspace Adaptation
Instructions are all you need: Self-supervised Reinforcement Learning for Instruction Following
Towards Order Fairness: Mitigating LLMs Order Sensitivity through Dual Group Advantage Optimization
Revitalizing Black-Box Interpretability: Actionable Interpretability for LLMs via Proxy Models
MedMCP-Calc: Benchmarking LLMs for Realistic Medical Calculator Scenarios via MCP Integration
Conditional Memory via Scalable Lookup: A New Axis of Sparsity for Large Language Models
MCP-Flow: Facilitating LLM Agents to Master Real-World, Diverse and Scaling MCP Tools
Beyond the Crowd: LLM-Augmented Community Notes for Governing Health Misinformation
Beyond the Final Actor: Modeling the Dual Roles of Creator and Editor for Fine-Grained LLM-Generated Text Detection
PILOT: Planning via Internalized Latent Optimization Trajectories for Large Language Models
MSEarth: A Multimodal Benchmark for Earth Science Phenomenon Discovery with MLLMs
Reasoning Structure Matters for Safety Alignment of Reasoning Models
Who Wrote This Line? Evaluating the Detection of LLM-Generated Classical Chinese Poetry
Representation Interventions Enable Lifelong Knowledge Memory Control in LLMs
SLoRA: Balancing Plasticity and Forgetting in Large Language Models for Continual Learning
Common to Whom? Regional Cultural Commonsense and LLM Bias in India
Par-ITA: Benchmarking Seq2Seq and LLMs on a Human-Supervised Parallel Corpus for Italian Hyperpartisan Neutralization
Demystifying Uncertainty in LLMs: Active Calibration between Concepts and Human Evaluations
LLM-VA: Resolving the Jailbreak-Overrefusal Trade-off via Vector Alignment
TiKMiX: Efficient Semi-Dynamic Data Mixture via Data Influence for LLM Pre-training
FlexGuard: Continuous Risk Scoring for Strictness-Adaptive LLM Content Moderation
AfriqueLLM: How Data Mixing and Model Architecture Impact Continued Pre-training for African Languages
What Does LLM Refinement Actually Improve? A Systematic Study on Document-Level Literary Translation
OctoBench: Benchmarking Scaffold-Aware Instruction Following in Repository-Grounded Agentic Coding
Editing the Moving World: Model Editing for Video LLMs
OCP: Outlier-Centric Probing for Dynamic Structured Pruning of LLMs
Attention Sinks Are Provably Necessary in Softmax Transformers: Evidence from Trigger-Conditional Tasks
AutoTaskEval: Towards Domain-Specific and Fine-Grained Evaluation for LLMs
CiteGuard: Faithful Citation Attribution for LLMs via Retrieval-Augmented Validation
From Insight to Action: A Novel Framework for Interpretability-Guided Data Selection in Large Language Models
UniSpec: Training-Free Speculative Decoding for Robust LLM Acceleration Across Languages and Hardware
Logical Consistency as a Bridge: Improving LLM Hallucination Detection via Label Constraint Modeling between Responses and Self-Judgments
FS-Researcher: Test-Time Scaling for Long-Horizon Research Tasks with File-System-Based Agents
A Mechanistic Account of Attention Sinks in GPT-2: One Circuit, Broader Implications for Mitigation
LLMs Enable Bag-of-Texts Representations for Short-Text Clustering
TriEx: A Game-based Tri-View Framework for Explaining Internal Reasoning in Multi-Agent LLMs
StealthGraph: Exposing Domain-Specific Risks in LLMs through Knowledge-Graph-Guided Harmful Prompt Generation
Integrating Data Validation with Large Language Models for Regulation-Guided Tabular Anomaly Detection
Faithful Serum: Mitigating the Faithfulness Gap in Textual Explanations of LLM Decisions via Attribution Guidance
Calibrating Inference Time Alignment with Sequence-level Risk Accumulation
QuantileMark: A Message-Symmetric Multi-bit Watermark for LLMs
HoWToBench: Holistic Evaluation for LLM’s Capability in Human-level Writing using Tree of Writing
Hierarchical Reinforcement Learning with Augmented Step-Level Transitions for LLM Agents
SeLaR: Selective Latent Reasoning in Large Language Models
GRAPHIA: Harnessing Social Graph Data to Enhance LLM-Based Social Simulation
SharedRequest: Privacy-Preserving Model‑Agnostic Inference for Large Language Models
Planning-Guided Tutoring with Assessment-Driven Memory for Pedagogical LLM Tutors
When KV Cache Reuse Fails in Multi-Agent Systems: Cross-Candidate Interaction is Crucial for LLM Judges
Evo-Attacker: Memory-Augmented Reinforcement Learning for Long-Horizon Tool Attacks on LLM-MAS
Reasoning Over Space: Enabling Geographic Reasoning for LLM-Based Generative Next POI Recommendation
Spectral Disentanglement: Rank-Aware Task Adaptation for Rehearsal-free Continual Learning in LLMs
StructMem: Structured Memory for Long-Horizon Behavior in LLMs
Arg-LLaDA: Argument Summarization via Large Language Diffusion Models and Sufficiency-Aware Refinement
Safety-Utility Conflicts Are Not Global: Surgical Alignment via Head-Level Diagnosis
Boundary-Guided Policy Optimization for Memory-efficient RL of Diffusion Large Language Models
ChartVerse: Scaling Chart Reasoning via Reliable Programmatic Synthesis from Scratch
arXiv2Table: Toward Realistic Benchmarking and Evaluation for LLM-Based Literature-Review Table Generation
SpeechLLM-as-Judges: Towards General and Interpretable Speech Quality Evaluation
HCSpec: Two-Tier Horizontal Cascade Speculative Decoding for High-Efficiency Large Language Model Inference
Revisiting the Reliability of Language Models in Instruction-Following
EfficientLLM: Unified Pruning-Aware Pretraining for Auto-Designed Compact Language Models
Enhancing the Transferability of Jailbreak Attacks on Large Language Models via Exploiting Reparameterization Invariance
GIFT: Guided Fine-Tuning and Transfer for Enhancing Instruction-Tuned Language Models
AMATA: Adaptive Multi-Agent Trajectory Alignment for Knowledge-Intensive Question Answering
ChessArena: A Chess Testbed for Evaluating Strategic Reasoning Capabilities of Large Language Models
From Completion to Editing: Unlocking Context-Aware Code Infilling via Search-and-Replace Instruction Tuning
From Word to World: Can Large Language Models be Implicit Text-based World Models?
GAMBIT: A Gamified Jailbreak Framework for Multimodal Large Language Models
Large Language Model-Enhanced Multi-Armed Bandits
Flattery in Motion: Benchmarking and Analyzing Sycophancy in Video-LLMs
A Survey of Large Language Model-Based Search Agents
The Reasoning Trap: How Enhancing LLM Reasoning Amplifies Tool Hallucination
Protecting multimodal large language models against misleading visualizations
Dual Activation-Weight Sparsity: A Training-Free Framework for Efficient Large Language Model Compression
Repeated Sequences Reveal Gaps between Large Language Models and Natural Language
Reasoning with OmniThought: A Large CoT Dataset with Verbosity and Cognitive Difficulty Annotations
InferenceDynamics: Adaptive LLM Routing through Structured Capability and Knowledge Profiling
Beyond Monolingual Assumptions: A Survey on Code-Switched NLP in the Era of Large Language Models across Modalities
Look Light, Think Heavy: What Multimodal Chain-of-Thought Reasoning Can and Cannot Do
ARCQuant: Boosting NVFP4 Quantization with Augmented Residual Channels for LLMs
MulVul: Retrieval-augmented Multi-Agent Code Vulnerability Detection via Cross-Model Prompt Evolution
When Correct Beliefs Collapse: Epistemic Resilience of LLMs under Clinical Pressure
Dissecting Failure Dynamics in Large Language Model Reasoning
SCVQ: Sparse-Compensated Vector Quantization for Large Language Models
Efficient KL Divergence Estimation via Truncated Top-K Integration for Large Language Models
VFA: Empoweing Multilingual MLLMs via Vision-Free Adaptation
Investigating More Explainable and Partition-Free Compositionality Estimation for LLMs: A Rule-Generation Perspective
Are LLMs Reliable Rankers? Rank Manipulation via Two-Stage Token Optimization
CoSToM: Causal-oriented Steering for Intrinsic Theory-of-Mind Alignment in Large Language Models
ConlangCrafter: Constructing Languages with a Multi-Hop LLM Pipeline
VAPO: End-to-end Slide-Enhanced Speech Recognition with Omni-modal Large Language Models
Data Mixing Agent: Learning to Re-weight Domains for Continual Pre-training
PAM: Enhancing General Alignment of Large Reasoning Models through Priority-Aware Metacognition
One Battle After Another: Probing LLMs’ Limits on Multi-Turn Instruction Following with a Benchmark Evolving Framework
Tracing the Roots: A Multi-Agent Framework for Uncovering Data Lineage in Post-Training LLMs
SGPVT: Self-Generated Proximal Visual Tokens for Mitigating Proximal Collateral Damage in MLLM Unlearning
VIGIL: Defending LLM Agents Against Tool-Stream Injection via Verify-Before-Commit
Sparrow: Text-Anchored Window Attention with Visual-Semantic Glimpsing for Speculative Decoding in Video LLMs
SPEAK: Spiking Neurons as an Entropy-Aware Tokenizer for Large Language Models
CTRAP: Embedding Collapse Trap to Safeguard Large Language Models from Harmful Fine-Tuning
Correct When Paired, Wrong When Split: Decoupling and Editing Modality-Specific Neurons in MLLMs
PLAWBENCH: A Rubric-Based Benchmark for Evaluating LLMs in Real-World Legal Practice
MT³: A Synergistic Multi-Task RL Framework for Specializing MLLMs in Text Image Machine Translation
Do LLMs Capture Embodied Cognition and Cultural Variation? Cross-Linguistic Evidence from Demonstratives
SGT: Securing Open-Source LLMs Against Malicious Fine-tuning via Safety Guidance Trigger
Every Token Counts: Generalizing 16M Ultra-Long Context in Large Language Models
Scaling External Knowledge Input Beyond Context Windows of LLMs via Multi-Agent Collaboration
FineLAP: Taming Heterogeneous Supervision for Fine-grained Language-Audio Pretraining
Mind the (DH) Gap! A Contrast in Risky Choices Between Reasoning and Conversational LLMs
From Experts to Bases: Orthogonal Subspace Mixture for Continual Multimodal Instruction Tuning
Masked by Consensus: Disentangling Privileged Knowledge in LLM Correctness
InstructDiff: Domain-Adaptive Data Selection via Contrastive Entropy for Efficient LLM Fine-Tuning
Visual Self-Fulfilling Alignment: Shaping Safety-Oriented Personas via Threat-Related Images
GRASPrune: Global Gating for Budgeted Structured Pruning of Large Language Models
Musical Score Understanding Benchmark: Evaluating Large Language Models’ Comprehension of Complete Musical Scores
Critical-CoT: A Robust Defense Framework against Reasoning-Level Backdoor Attacks in Large Language Models
How Do LLMs and VLMs Understand Viewpoint Rotation Without Vision? An Interpretability Study
Sycophants in the Courtroom: Are LLMs Fragile to Juridical Authority and Evolving Legal Standards?
Valid Survey Simulations with Limited Human Data: The Roles of Prompting, Fine-Tuning, and Rectification
CuBridge: An LLM-Based Framework for Understanding and Reconstructing High-Performance Attention Kernels
Defenses Against Prompt Attacks Learn Surface Heuristics
Memory-Augmented LLM-based Multi-Agent System for Automated Feature Generation on Tabular Data
Learning from the Irrecoverable: Error-Localized Policy Optimization for Tool-Integrated LLM Reasoning
Learning from Evolving Training Dynamics: An Entropy-Maximizing Data Curation Strategy for LLM Supervised Post-Training
Reinforcement Learning on Pre-Training Data
CreditDecoding: Accelerating Parallel Decoding in Diffusion Large Language Models with Trace Credit
Question Difficulty Estimation for Large Language Models via Answer Plausibility Scoring
DMN: A Compositional Framework for Jailbreaking Multimodal LLMs with Multi-Image Inputs
PIAST: Rapid Prompting with In-context Augmentation for Scarce Training data
SafeMCP: Proactive Power Regulation for LLM Agent Defense via Environment-Grounded Look-Ahead Reasoning
LLaDA 1.5: Variance-Reduced Preference Optimization for Large Language Diffusion Models
HarmRLVR: Weaponizing Verifiable Rewards for Harmful LLM Alignment
Just Pass Twice: Efficient Token Classification with LLMs for Zero-Shot NER
SHAPE: Unifying Safety, Helpfulness and Pedagogy for Educational LLMs
Evolving Sparsity: Leveraging Token Importance Dynamics for Efficient LLM Decoding with Sparse Attention
MOA: Multi-Objective Alignment for Role-Playing Agents
Losing our Tail, Again: (Un)Natural Selection & Multilingual LLMs
Chain-of-Memory: Lightweight Memory Construction with Dynamic Evolution for LLM Agents
Efficient Test-Time Scaling of Multi-Step Reasoning by Probing Internal States of Large Language Models
Adaptive Prompt Structure Factorization: A Framework for Self-Discovering and Optimizing Compositional Prompt Programs
Cognitive Alpha Mining via LLM-Driven Code-Based Evolution
KV-Embedding: Training-free Text Embedding via Internal KV Re-routing in Decoder-only LLMs
Fingerprinting LLMs via Prompt Injection
Exploring Layer Activation Dynamic of CoT via Knowledge Probe
From Trust to Compromise: Outcome-Verified LLM Phishing Simulation and Real-Time Defense
DecoCal: Decoding with Calibration in Diffusion Large Language Models
LiveFact: A Dynamic, Time-Aware Benchmark for LLM-Driven Fake News Detection
Beyond “I Don’t Know”: Evaluating LLM Self-Awareness in Discriminating Data and Model Uncertainty
Unlearners Can Lie: Evaluating and Improving Honesty in LLM Unlearning
Diffusion-CAM: Faithful Visual Explanations for dMLLMs
Beyond Noise: Characterizing Creative Potential in Unverifiable LLM Hallucinations
LLM-SLM Collaborative Framework of Idiomatic Expression Generation
Focus-dLLM: Accelerating Long-Context Diffusion LLM Inference via Confidence-Guided Context Focusing
Table Question Answering in the Era of Large Language Models: A Comprehensive Survey of Tasks, Methods, and Evaluation
Patches of Nonlinearity: Instruction Vectors in Large Language Models
Reasoning Gets Harder for LLMs Inside A Dialogue
PDR: A Plug-and-Play Positional Decay Framework for LLM Pre-training Data Detection
Deep Kernel Fusion for Transformers
Generative Gamer: Learning Equilibrium Strategy by LLM-driven Dynamic Deduction
A Scalable Multi-LLM Collaboration System with Retrieval-based Selection and Exploration-Exploitation-Driven Enhancement
LLM-as-Scheduler: Agentic Workflow Dynamic Scheduling
Memory-R1: Enhancing Large Language Model Agents to Manage and Utilize Memories via Reinforcement Learning
CostBench: Evaluating Multi-Turn Cost-Optimal Planning and Adaptation in Dynamic Environments for LLM Tool-Use Agents
Making Large Language Models Efficient Dense Retrievers
Lightweight LLM Agent Memory with Small Language Models
HybridKV: Hybrid KV Cache Compression for Efficient Multimodal Large Language Model Inference
Arguments that Alter Minds: LLM Rationales Sway Human (and LLM) Notions of Plausibility
Vista-LLM: Decoupled Query-Guided Visual Token Pruning for Efficient Long-Video Large Language Models
Scaling Law for Multimodal Large Language Model Supervised Fine-Tuning
IUQ: Interrogative Uncertainty Quantification for Long-Form Large Language Model Generation
Answering the Wrong Question: Reasoning Trace Inversion for Abstention in LLMs
SpiderFlow: Efficient Topology-Aware Scheduling for LLM Training Across Decentralized GPU Clusters
Unleashing Spatial Reasoning in Multimodal Large Language Models via Textual Representation Guided Reasoning
Why Multimodal In-Context Learning Lags Behind? Unveiling the Inner Mechanisms and Bottlenecks
HeLa-Mem: Hebbian Learning and Associative Memory for LLM Agents
Can Factual Opinions Be Edited (Manipulated) in Large Language Models?
Language of Thought Shapes Output Diversity in Large Language Models
Aligning Backchannel and Dialogue Context Representations via Contrastive LLM Fine-Tuning
Verifiable LLM-Generated Text Detection via Projected Semantic-Structural Distributions
Communication-Efficient Desire Alignment for Proactive Embodied Human–Agent Interaction
ICDAGENT: Empowering Agentic Large Language Models for Explainable Medical Coding
Iterative Dual-Model Alignment for Story Evaluation
LLMs Underperform Graph-Based Parsers on Supervised Relation Extraction for Complex Graphs
Talking to a Know-It-All GPT or a Second-Guesser Claude? How Repair reveals distinct Multi-Turn Behavior in LLMs
What Makes LLMs Effective Sequential Recommenders? A Study on Preference Intensity and Temporal Context
FinChain: A Symbolic Benchmark for Verifiable Chain-of-Thought Financial Reasoning
For-Value: Efficient Forward-Only Data Valuation for finetuning LLMs and VLMs
PARASITE: Conditional System Prompt Poisoning to Hijack LLMs
XMark: Reliable Multi-Bit Watermarking for LLM-Generated Texts
CASPER in the Machine: Insights into Character Variety in LLM-Generated Stories
Language Models Struggle to Use Representations Learned In-Context
Rethinking Evaluation for LLM Hallucination Detection: A Desiderata, A New RAG-based Benchmark, New Insights
PRIME: A Process-Outcome Alignment Benchmark for Verifiable Reasoning in Mathematics and Engineering
ZARA: Training-Free Motion Time-Series Reasoning via Evidence-Grounded LLM Agents
AutoJudger: An Agent-Driven Framework for Efficient Benchmarking of MLLMs
The Imperfective Paradox in Large Language Models
Attention Under Attack: Analog Noise Effects and Mechanistic Vulnerabilities in Transformer Models
How to Improve LLMs’ Performance on Specific Languages: A Perspective on LLM-Derived Language Similarity
MATCH: Modulating Attention via In‑Context Retrieval for Long‑Context Transformers
Protecting Bystander Privacy via Selective Hearing in Audio LLMs
LiveCLKTBench: Towards Reliable Evaluation of Cross-Lingual Knowledge Transfer in Multilingual LLMs
To Lie or Not to Lie? Investigating The Biased Spread of Global Lies by LLMs
Adaptive Constraint Propagation: Scaling Structured Inference for Large Language Models via Meta-Reinforcement Learning
STReasoner: Empowering LLMs for Spatio-Temporal Reasoning in Time Series via Spatial-Aware Reinforcement Learning
Hallucination Detection in LLMs with Topological Divergence on Attention Graphs
Mediocrity is the key for LLM as a Judge Anchor Selection
To Think or Not to Think: The Hidden Cost of Meta-Training with Excessive CoT Examples
ReproEvalCard: A Reporting Standard for Reproducible Evaluation of LLM Pipelines
LLM Agents in Law: Taxonomy, Applications, and Challenges
Not All Tokens Matter: Towards Efficient LLM Reasoning via Token Significance in Reinforcement Learning
Evaluating Robustness of Large Language Models Against Multilingual Typographical Errors
MediEval: A Unified Medical Benchmark for Patient-Contextual and Knowledge-Grounded Reasoning in LLMs
Accommodation and Epistemic Vigilance: A Pragmatic Account of Why LLMs Fail to Challenge Harmful Beliefs
Every Response Counts: Quantifying Uncertainty of LLM-based Multi-Agent Systems through Tensor Decomposition
Uncertainty Quantification in LLM Agents: Foundations, Emerging Challenges, and Opportunities
Guided by Gut: Efficient Test-Time Scaling with Reinforced Intrinsic Confidence
Narrative License and Model Sycophancy in LLM Summaries of Scientific Work
AlignUSER: Human-Aligned LLM Agents via World Models for Recommender System Evaluation
CoAct: Co-Active LLM Preference Learning with Human-AI Synergy
Label and Explanation Variation in LLM-Based Annotation: a Case Study in Natural Language Inference
Text-Attributed Knowledge Graph Enrichment with Large Language Models for Medical Concept Representation
Why LLM Safety Guardrails Collapse After Fine-tuning: A Similarity Analysis Between Alignment and Fine-tuning Datasets
Check Your Work: Structured Checklist Feedback for Improving Large Language Models
LOKA: Conflict-Aware LLM Knowledge Update with Adaptive Knowledge Memory
When LLMs Read Tables Carelessly: Measuring and Reducing Data Referencing Errors
Decoupling Task-Solving and Output Formatting in LLM Generation
Mind the Gap in Cultural Alignment: Task-Aware Culture Management for Large Language Models
Analyzing and Internalizing Complex Policy Documents for LLM Agents
In-Context Representation Hijacking
Quantifying Metric and Model Agreement in Bias Evaluation of Large Language Models
MultiFinBen: Benchmarking Large Language Models for Multilingual and Multimodal Financial Application
Do LLMs Really Need 10+ Thoughts for “Find the Time 1000 Days Later”? Towards Structural Understanding of LLM Overthinking
When One LLM Drools, Multi-LLM Collaboration Rules
Select Before Use: On the Importance of Reference Model Selection in Preference Alignment
VOYAGER: A Training Free Approach for Generating Diverse Datasets using LLMs
From Inheritance to Saturation: Disentangling the Evolution of Visual Redundancy for Architecture-Aware MLLM Inference Acceleration
What Do LLMs Learn First? Asymmetric Learning Dynamics of Input Complexity and Output Ambiguity in Preference Alignment
Multi-Agent-as-Judge: Aligning LLM-Agent-Based Automated Evaluation with Multi-Dimensional Human Evaluation
OpenRubrics: Towards Scalable Synthetic Rubric Generation for Reward Modeling and LLM Alignment
Challenging the Boundaries of Reasoning: An Olympiad-Level Math Benchmark for Large Language Models
LENS: LLM-Enabled Narrative Synthesis for Mental Health by Aligning Multimodal Sensing with Language Models
FedProxy: Federated Fine-Tuning of LLMs via Proxy SLMs and Heterogeneity-Aware Fusion
DiZiNER: Disagreement-guided Instruction Refinement via Simulating Pilot Annotation for Zero-shot Named Entity Recognition
Free Energy-Driven Reinforcement Learning with Adaptive Advantage Shaping for Unsupervised Reasoning in LLMs
ETR: Entropy Trend Reward for Efficient Chain-of-Thought Reasoning
Controlling Distributional Bias in Multi-Round LLM Generation via KL-Optimized Fine-Tuning
On the Continued Value of Universal Dependencies in the Era of Large Language Models
Adaptive Text2GQL: Integrating Structural Twig Linking and Evolutionary In-Context Learning
XToM: Exploring the Multilingual Theory of Mind for Large Language Models
Cognitive Policy-Driven LLM for Diagnosis and Intervention of Cognitive Distortions in Emotional Support Conversation
Immediate Inference: The Missing Foundation in Large Language Model Logical Reasoning
Reference Attack: A New Cross-Modal Jailbreaking Attack against Multimodal Large Language Models
POWSM: A Phonetic Open Whisper-Style Speech Foundation Model
CIA: Inferring the Communication Topology from LLM-based Multi-Agent Systems
AdvancedIF: Rubric-Based Benchmarking and Reinforcement Learning for Advancing LLM Instruction Following
Long-Chain Reasoning Distillation via Adaptive Prefix Alignment
TRN-R1-Zero: Text-rich Network Reasoning via LLMs with Reinforcement Learning Only
Beyond Value Benchmarks: Measuring Value-Structure Alignment in Large Language Models via Symmetric Q-Sorts
Would LLMs be Good Historical Linguists and Chinese Dialect Learners?
Seeing No Evil: Blinding Large Vision-Language Models to Safety Instructions via Adversarial Attention Hijacking
CADMate: Generating CAD Assembly Plan with Geometric Chain-of-Thought and Spatial Physical Rewards
Calibration-Aware Policy Optimization for Reasoning LLMs
Beyond End-to-End: Dynamic Chain Optimization for Private LLM Adaptation on the Edge
TalkLoRA: Communication-Aware Mixture of Low-Rank Adaptation for Large Language Models
TARE: Lightweight Token-Aware Representation Editing for Fine-tuning Transformer-like Models
Soft Orthogonal Low-Rank Adaptation for Knowledge Sharing in Large Language Model Continual Learning
Curing Miracle Steps in LLM Mathematical Reasoning with Rubric Rewards
Team-Based Self-Play With Dual Adaptive Weighting for Fine-Tuning LLMs
Enhancing Linguistic Competence of Language Models through Pre-training with Language Learning Tasks
FineSteer: A Unified Framework for Fine-Grained Inference-Time Steering in Large Language Models
ToolPRM: Fine-Grained Inference Scaling of Structured Outputs for Function Calling
Closing the Modality Reasoning Gap for Speech Large Language Models
Logical Phase Transitions: Understanding Collapse in LLM Logical Reasoning
Mitigating Catastrophic Forgetting in Target Language Adaptation of LLMs via Source-Shielded Updates
TLSA: LLM-Guided Text-Label Space Alignment with Contrastive Learning for Generalized Category Discovery
Hierarchical Token Prepending: Enhancing Information Flow in Decoder-based LLM Embeddings
StoryCoder: Narrative Reformulation for Structured Reasoning in LLM Code Generation
ODL-TempLLM: Ontology-Guided and Description Logic-Reasoned Temporal Reasoning with LLMs
Your Students Don’t Use LLMs Like You Wish They Did
BWLA: Breaking the Barrier of W1AX Post-Training Quantization for LLMs
Dynamics of Cognitive Heterogeneity: Investigating Behavioral Biases in Multi-Stage Supply Chains with LLM-Based Simulation
Chain-of-Thought Compression Should Not Be Blind: V-Skip for Efficient Multimodal Reasoning via Dual-Path Anchoring
CodeJudgeBench: Benchmarking LLM-as-a-Judge for Coding Tasks
Modeling LLM Unlearning as an Asymmetric Two-Task Learning Problem
MVP: Enhancing Video Large Language Models via Self-supervised Masked Video Prediction
Maximizing Local Entropy Where It Matters: Prefix-Aware Localized LLM Unlearning
Language Acquisition Device in Large Language Models
ReFL: Reflective Feedback Learning for Hallucination Detection of Large Language Models
Fine-Mem: Fine-Grained Feedback Alignment for Long-Horizon Memory Management
NaturalSloth: Revisiting Denial-of-Service Attacks on Large Language Models
Distillation Traps and Guards: A Calibration Knob for LLM Distillability
DVMap: Fine-Grained Pluralistic Value Alignment via High-Consensus Demographic-Value Mapping
IS-CoT: Breaking the Long-form Generation Collapse via Interleaved Structural Thinking
Seeing the Whole Elephant: A Benchmark for Failure Attribution in LLM-based Multi-Agent Systems
Why LLMs Hallucinate on Structured Knowledge: A Mechanistic Analysis of Reasoning over Linearized Representations
Merlin’s Whisper: Enabling Efficient Reasoning in Large Language Models via Black-box Persuasive Prompting
CAKE: Causal-Guided Adaptive Knowledge Editing for LLMs
Less is More: Improving LLM Reasoning with Minimal Test-Time Intervention
League of LLMs: A Benchmark-Free Paradigm for Mutual Evaluation of Large Language Models
Rethinking Data Mixing from the Perspective of Large Language Models
The Paradox of Outcome Optimization: A Causal Information-Theoretic Bound on Reasoning Shortcuts in LLMs
Uncovering Sentiment Analysis Circuit in Large Language Model
ReEfBench: Quantifying the Reasoning Efficiency of LLMs
Beyond Ranking: Fine-Grained Diagnostics and Self-Improvement for MLLMs
Bridging Internal Consistency and External Alignment: A Causal and Dynamic Interpretability Framework for LLM Generation
Toward Robust In-Context Learning: Leveraging Out-of-distribution Proxies for Target Inaccessible Demonstration Retrieval
Breaking Block Boundaries: Anchor-based History-stable Decoding for Diffusion Large Language Models
HiSVD: Principled Low-Rank Approximation of LLMs via Hierarchical Modeling of Information Capacity and Spectral Structure
Language on Demand, Knowledge at Core: Composing LLMs with Encoder-Decoder Translation Models for Extensible Multilinguality
Fisher-Driven Adaptive Locating for Knowledge Editing in Large Language Models
From AR to Diffusion: Efficiently Adapting Large Language Models with Strictly Causal and Elastic Horizons
ExPerT: Personalizing LLM Responses to Users’ Domain Expertise via Query-Wise Semantic and Keystroke Behavioral Cues
Cultural Benchmarking of LLMs in Standard and Dialectal Arabic Dialogues
ReRec: Reasoning-Augmented LLM-based Recommendation Assistant via Reinforcement Fine-tuning
MoA: Heterogeneous Mixture of Adapters for Parameter-Efficient Fine-Tuning of Large Language Models
Beyond the Context Window: Scaling Agentic RL via End-to-end Optimized Context Compression
Probing the Safety Robustness of LLMs in Latent Space
LoopTool: Closing the Data–Training Loop for Robust LLM Tool Calls
USB: A COMPREHENSIVE AND UNIFIED SAFETY EVALUATION BENCHMARK FOR MULTIMODAL LARGE LANGUAGE MODELS
LLMEval-Fair: A Large-Scale Longitudinal Study on Robust and Fair Evaluation of Large Language Models
Controllable LLM Reasoning via Sparse Autoencoder‑Based Steering
The GaoYao Benchmark: A Comprehensive Framework for Evaluating Multilingual and Multicultural Abilities of Large Language Models
Agentic Memory: Learning Unified Long-Term and Short-Term Memory Management for Large Language Model Agents
Profiling-Free Mixed-Precision Quantization for MoE LLMs via Fuzzy Rule Interpolation
EduBench: A Comprehensive Benchmarking Dataset for Evaluating Large Language Models in Diverse Educational Scenarios
MMAC: A Multilingual, Multimodal Alignment Framework for Cultural Grounding Evaluation
Traffic-R1: Reinforced LLMs Bring Human-Like Reasoning to Traffic Signal Control Systems
BoYaEval: Evaluating Multimodal Large Language Models on Understanding Ancient Chinese Musical Scores
Perplexity-Aware Data Scaling Law: Perplexity Landscapes Predict Performance for Continual Pre-training
How Can Synthetic Data Improve Multilingual Language Model Pretraining? A Data Quality Perspective
Can Large Language Models Infer Causal Relationships from Real-World Text?
Distributional Clarity: The Hidden Driver of RL-Friendliness in Large Language Models
Task-Aware LLM Routing with Multi-Level Task-Profile-Guided Data Synthesis for Cold-Start Scenarios
MACS: Modality-Aware Capacity Scaling for Efficient Multimodal MoE Inference
Markovian Linguistic-Temporal Bridge: Unlocking the Potential of LLMs for Time Series Forecasting
FLARE: Fine-Grained Length-Aware Routing for Resource-Efficient Heterogeneous LLM Serving
Bit-by-Bit: Progressive QAT Strategy with Outlier Channel Splitting for Stable Low-Bit LLMs
Learning from Cognition: Enhancing RL Efficiency for LLM Reasoning via Hierarchical Metacognitive Decomposition and Refinement
EpiCaR: Knowing What You Don’t Know Matters for Better Reasoning in LLMs
Omni-Embed-Audio: Leveraging Multimodal LLMs for Robust Audio-Text Retrieval
SPIO: Ensemble and Selective Strategies via LLM-Based Multi-Agent Planning in Automated Data Science
Causal2Vec: Improving Decoder-only LLMs as Embedding Models through a Contextual Token
Enhancing Multimodal Large Language Models for Ancient Chinese Character Evolution Analysis via Glyph-Driven Fine-Tuning
See2Refine: Vision-Language Feedback Improves LLM-Based eHMI Action Designers
A Survey of Reinforcement Learning for Large Language Models under Data Scarcity: Challenges and Solutions
SADA: Bridging In-Context Learning and Fine-Tuning via State-Aligned Distillation Adapters
Large Language Models Are Bad Dice Players: LLMs Struggle to Generate Random Numbers from Statistical Distributions
PROMPRINT: Prompt Fingerprinting via First-Token Response for LLM App Cloning Detection
CoEvolve: Training LLM Agents via Agent-Data Mutual Evolution
Make LLMs See Like Investigators, Not Just Think More: The Role of Structured Analysis in Investigative Reasoning
From Narrow Unlearning to Emergent Misalignment in LLMs
MUR: Momentum Uncertainty guided Reasoning for Large Language Models
How Training Data Shapes the Use of Parametric and In-Context Knowledge in Language Models
BTC-LLM: Efficient Sub-1-Bit LLM Quantization via Learnable Transformation and Binary Codebook
GrACE: A Generative Approach to Better Confidence Elicitation and Efficient Test-Time Scaling in Large Language Models
Understanding Structured Financial Data with LLMs: A Case Study on Fraud Detection
Gap-K%: Measuring Top-1 Prediction Gap for Detecting Pretraining Data
Are they lovers or friends? Evaluating LLMs’ Social Reasoning in English and Korean Dialogues
Detoxification for LLM: From Dataset Itself
Instant Personalized Large Language Model Adaptation via Hypernetwork
Safeguarding LLM Fine-tuning via Push-Pull Distributional Alignment
See the Forest for the Trees: Loosely Speculative Decoding via Visual-Semantic Guidance for Efficient Inference of Video LLMs
LaoBench: A Large-Scale Multidimensional Lao Benchmark for Large Language Models
Gradient-Guided Multi-Judge Prompt Optimization
IF-RewardBench: Benchmarking Judge Models for Instruction-Following Evaluation
Beyond Meta-Reasoning: Metacognitive Consolidation for Self-Improving LLM Reasoning
Mnemis: Dual-Route Retrieval on Hierarchical Graphs for Long-Term LLM Memory
Consolidation or Adaptation? PRISM: Disentangling SFT and RL Data via Gradient Concentration
Scaling Laws for Code: A More Data-Hungry Regime
VRPO: Rethinking Value Modeling for Robust RL under Noisy Supervision in LLM Post-Training
Taming Actor-Observer Asymmetry in Agents via Dialectical Alignment
KoCo: Conditioning Language Model Pre-training on Knowledge Coordinates
Truth or Sophistry? LoFa: A Benchmark for LLM Robustness Against Logical Fallacies
Merging Triggers, Breaking Backdoors: Defensive Poisoning for Instruction-Tuned Language Models
SHAPE: Stage-aware Hierarchical Advantage via Potential Estimation for LLM Reasoning
Looking Beyond the One: Operationalizing and Eliciting Visual Ambiguity in VLLMs
Safe-FedLLM: Delving into the Safety of Federated Large Language Models
ImCoref-CeS: An Improved Lightweight Pipeline for Coreference Resolution with LLM-based Checker-Splitter Refinement
When Efficiency Meets Safety: A Benchmark Security Analysis of KV Cache Compression in Large Language Models
WebAggregator: Enhancing Compositional Reasoning Capabilities of Deep Research Agent Foundation Models
Good Arguments Against the People Pleasers: How Reasoning Mitigates (Yet Masks) LLM Sycophancy
Can Persona-Prompted LLMs Emulate Subgroup Values? An Empirical Analysis of Generalisability and Fairness in Cultural Alignment
Adaptive Spatial and Temporal Redundancy Optimization for Efficient Reasoning in Large Language Models
AAPO: Enhancing the Reasoning Capabilities of LLMs with Advantage Margin
Learning to Edit Knowledge via Instruction-based Chain-of-Thought Prompting
BadScientist: Can a Research Agent Write Convincing but Unsound Papers that Fool LLM Reviewers?
DFAMS: Dynamic-flow guided Federated Alignment based Multi-prototype Search
PARIF: Pushing the Pareto Frontier of Instruction Following and Reasoning with Curriculum Reinforcement Learning
GeoLaux: A Benchmark for Evaluating MLLMs’ Geometry Performance on Long-Step Problems Requiring Auxiliary Lines
Unlocking Multilingual Reasoning Capability of LLMs and LVLMs through Representation Engineering
Into the Gray Zone: Domain Contexts Can Blur LLM Safety Boundaries
Psyche-R1: Towards Reliable Psychological LLMs through Unified Empathy, Expertise, and Reasoning
IF-CRITIC: Towards a Fine-Grained LLM Critic for Instruction-Following Evaluation
Know Your Place: Diagnosing Implicit Social Adaptation Failures in Chinese Large Language Models
Locomo-Plus: Beyond-Factual Cognitive Memory Evaluation Framework for LLM Agents
VLN-NF: Feasibility-Aware Vision-and-Language Navigation with False-Premise Instructions
NiuTrans.LMT: Toward Inclusive and Scalable Multilingual Machine Translation with LLMs
MERIT Feedback Elicits Better Bargaining in LLM Negotiators
GMFL: Efficient Global Masking for Federated LLM Fine-tuning
AgentGL: Towards Agentic Graph Learning with LLMs via Reinforcement Learning
MM-JudgeBias: A Benchmark for Evaluating Compositional Biases in MLLM-as-a-Judge
ReLook: Vision-Grounded RL with a Multimodal LLM Critic for Agentic Web Coding
Learning to Think on Hypergraph: HyperCoT for Structure-Guided N-ary Knowledge Graph Completion
Two Pathways to Truthfulness: On the Intrinsic Encoding of LLM Hallucinations
LLM-ForcedAligner: A Non-Autoregressive and Accurate LLM-Based Forced Aligner for Multilingual and Long-Form Speech
Latent-Condensed Transformer for Efficient Long Context Modeling
CrossGuard: Safeguarding MLLMs against Joint-Modal Implicit Malicious Attacks
ImF: Embedding an Implicit Fingerprint in Your Large Language Models
Jailbreaking Multimodal Large Language Models using Multi-Clip Video
Towards Privacy-Preserving Large Language Model: Text-free Inference Through Alignment and Adaptation
Selective Knowledge Distillation: Fusing LLM Semantic Strengths with DNN Efficiency for Binary Code Similarity Detection
TransLLM: A Unified Multi-Task Large Language Model for Urban Transportation via Learnable Prompting
Stop Fixating on Prompts: Reasoning Hijacking and Constraint Tightening for Red-Teaming LLM Agents
Attention Basin: Why Contextual Position Matters in Large Language Models
Beyond Surface Features: Advancing Medical Vision-Language Alignment via Dynamic Evidence-Guided Preference Optimization
TinyJudge: Unverifiable Constraint Alignment via Lightweight Specialist Ensembles
Dynamic Infilling Anchors for Format-Constrained Generation in Diffusion Large Language Models
Inhibitory Attacks on Backdoor-based Fingerprinting for Large Language Models
TimeSAF: Towards LLM-Guided Semantic Asynchronous Fusion for Time Series Forecasting
Pruning Unsafe Tickets: A Resource-Efficient Framework for Safer and More Robust LLMs
Cat-MoD: Accelerating Multimodal Alignment via Caption Token Guided Asymmetric Mixture-of-Depths
Beyond Scaling: Measuring and Predicting the Upper Bound of Knowledge Retention in Language Model Pre-Training
Efficient Paths and Dense Rewards: Probabilistic Flow Reasoning for Large Language Models
TriPlay-RL: Tri-Role Self-Play Reinforcement Learning for LLM Safety Alignment
Cross-Modal Coreference Alignment: Enabling Reliable Information Transfer in Omni-LLMs
MPBoCo: Multimodal Prompt-based Boundary-enhanced Continual Framework for Joint Entity and Relation Extraction
Personalizing LLMs with Binary Feedback: A Preference-Calibrated Optimization Framework
AIM-CoT: Active Information-driven Multimodal Chain-of-Thought for Vision-Language Reasoning
Benchmarking Egocentric Clinical Intent Understanding Capability for Medical Multimodal Large Language Models
False Friends in the Shell: Unveiling the Emoticon Semantic Confusion in Large Language Models
LLM Reasoning as Trajectories: Step-Specific Representation Geometry and Correctness Signals
A Data-Efficient Path to Multilingual LLMs: Language Expansion via Post-training PARAMΔ Integration into Upcycled MoE
The Evolution of Thought: Tracking LLM Overthinking via Reasoning Dynamics Analysis
Can LLMs Estimate Cognitive Complexity of Reading Comprehension Items?
Human or LLM as Standardized Patients? A Comparative Study in Medical Education
Harmonizing the Past, Present, and Future: A Null-Space Constrained Region-Specific Method for Continual Learning in LLMs
Inertia in Moral and Value Judgments of Large Language Models
LiveCultureBench: a Multi-Agent, Multi-Cultural Benchmark for Large Language Models in Dynamic Social Simulations
LADR: Locality-Aware Dynamic Rescue for Efficient Text-to-Image Generation with Diffusion Large Language Models
PACE: Predictive Adaptive Context Extraction for Long-Horizon LLM Agents
Draft, Verify, Restore: Self-Refining Historical Inscription Restoration with a Unified MLLM
SAM3-I: Segment Anything with Instructions
Stop When Enough: Adaptive Early-Stopping for Chain-of-Thought Reasoning
CaRL-EM: Cost-Aware Reinforcement Learning for Entity Matching with LLMs
Demystifying Data Organization for Enhanced LLM Training
Beyond Single View: A Comprehensive Benchmark for Medical Multimodal Large Language Models on Multi-Image Understanding
When Seeing Is not Enough: Revealing the Limits of Active Reasoning in MLLMs
CuMA: Aligning LLMs with Sparse Cultural Values via Demographic-Aware Mixture of Adapters
Selective Span-Level Unlearning for Large Language Models
ToMMeR - Efficient Entity Mention Detection from Large Language Models
Shuttle Between Symbolic Instructions and Neural Parameters of Large Language Models
Efficient Hyperparameter Optimization for LLM Reinforcement Learning
Hetero-Designer: Automated Design of Multi-Agent Systems with Heterogeneous LLMs
Achieving Multi-Hop Calculation and Safe Abstention in Financial Numerical Reasoning by Metric Graph Constrained LLMs
MemBuilder: Reinforcing LLMs for Long-Term Memory Construction via Attributed Dense Rewards
Probing Semantic Alignment, Lexical Invariance, and Syntactic Influence in LLM Metaphor Processing
MathCanvas: Intrinsic Visual Chain-of-Thought for Multimodal Mathematical Reasoning
Calibrated? Not for Everyone: How Sexual Orientation and Religious Markers Distort LLM Accuracy and Confidence in Medical QA
Rethinking the Role of Entropy in Optimizing Tool-Use Behaviors for Large Language Model Agents
LLM-MC-Affect: LLM-Based Monte Carlo Modeling of Affective Trajectories and Latent Ambiguity for Interpersonal Dynamic Insight
UniSonate: A Unified Model for Speech, Music, and Sound Effect Generation with Text Instructions
VCORE: Variance-Controlled Optimization-based Reweighting for Chain-of-Thought Supervision
VLN-MME: Diagnosing MLLMs as Language-guided Visual Navigation Agents
ImplicitMemBench: Measuring Unconscious Behavioral Adaptation in Large Language Models
VerilogLAVD: LLM-Aided Pattern Generation for Verilog CWE Detection
Temporal Sampling for Forgotten Reasoning in LLMs
STAPO: Selective Trajectory-Aware Policy Optimization for LLM Agent Training
OASIS: Mitigating Harmful Fine-tuning Attacks on LLMs via Orthogonal and Adaptive Safety Alignment Strategy
KoCo-Bench: Can Large Language Models Leverage Domain Knowledge in Software Development?
MagicBench: Diagnosing Visual Agency Loss and Semantic Dependency in Multimodal LLMs
Fair-CCD: Mitigating Bias in Large Language Models for Tabular Classification Through Context-Contrastive Decoding
GMSA: Enhancing Context Compression via Group Merging and Layer Semantic Alignment
From Knowing to Teaching: Scaffolding Pedagogical Decisions for LLM Agent
Think Faster Than Words: Efficient LLM Chain-of-Thought Reasoning via Dynamic Shortcut Decoding
AEA: Adaptive Expert Allocation Improves Sentence Embeddings from Mixture-of-Experts LLM
N-GLARE: An Non-Generative Latent Representation-Efficient LLM Safety Evaluator
Beyond Static Persona Consistency: Dynamic Persona Coherence in LLM Role-Playing
Why Are We Moral? An LLM-based Agent Simulation Approach to the Study of Moral Evolution
On the (In-)Security of the Shuffling Defense in the Transformer Secure Inference
LaCo: Layer-wise Compensation for Pruned Large Language Models
Location Not Found: Exposing Implicit Local and Global Biases in Multilingual LLMs
LLMs in Sarcasm Detection? It’s elementary! (Or is it?)
TLoRA: Task-aware Low Rank Adaptation of Large Language Models
LLMs as Knowledge Graph Refiners: Mitigating Factual Inconsistencies in Generative Knowledge Extraction
SILO-BENCH: A Scalable Environment for Evaluating Distributed Coordination in Multi-Agent LLM Systems
Mitigating Structural Knowledge Collapse in Domain-Specific LLMs via Morpheme-Aware KV-Aggregation
Whose Facts Win? LLM Source Preferences under Knowledge Conflicts
EGSS: Entropy-guided Stepwise Scaling for Reliable Software Engineering
Detecting What Queries Seek: Steering LLM Safety with FFN Output Activation Monitoring
Temporal Evidence Chain for Temporal Knowledge Graph Question Answering with Large Language Models
UERLens: Understanding Event Relations in Large Language Models
DEFT: Demystifying VLN Failures via a Unified Dual-View Explainability Framework for LLM-based Agents
LLMs (Almost) Never Abstain Under Medical Uncertainty
TOWER+: Bridging Generality and Translation Specialization in Multilingual LLMs
Culture-Aware Machine Translation in Large Language Models: Benchmarking and Investigation
LongTutor: Benchmarking Large Language Models for Long-term Personalized Tutoring
Understanding and Mitigating Political Stance Cross-topic Generalization in Large Language Models
Can LLMs Act as Historians? Evaluating Historical Research Capabilities of LLMs via the Chinese Imperial Examination
Less Languages, Less Tokens: An Efficient Unified Logic Cross-lingual Chain-of-Thought Reasoning Framework
Embracing Anisotropy: Turning Massive Activations into Interpretable Control Knobs for Large Language Models
One Cognitive Loop Is Enough: SODA unlocks Pure-Text Spatial Reasoning in Large Language Models
Compatibility-Aware Dynamic Fine-Tuning for Large Language Models
Reusable Experiences: Latent Routing and Modular Composition in LLMs
Controllable Contamination Detection for Reliable LLM Evaluation with Statistical Guarantees
From 1,000,000 Users to Every User: Scaling Up Personalized Preference for User-level Alignment
Beyond Atomic Characters: Glyph-Aware Sub-character Alignment for Low-Resource Multilingual OCR
Why Supervised Fine-Tuning Fails to Learn: A Systematic Study of Incomplete Learning in Large Language Models
Towards Interpretable Tabular Reasoning: Enhancing LLM Reasoning on Tabular Data with Pre-Constructed Logic Graph
Compressing LLM Knowledge into Graph Representations for Text-attributed Graphs Learning
End-to-End Optimization of LLM-Driven Multi-Agent Search Systems via Heterogeneous-Group-Based Reinforcement Learning
Understanding Emergent Misalignment via Feature Superposition Geometry
Optimizing RAG Rerankers with LLM Feedback via Reinforcement Learning
Explainable and Fine-Grained Safeguarding of LLM Multi-Agent Systems via Bi-Level Graph Anomaly Detection
Understanding and Mitigating Bias Inheritance in LLM-based Data Augmentation on Downstream Tasks
Beyond the Panorama: Training-Free Hierarchical Perception-Reasoning for Fine-Grained Vision in MLLMs
To Judge or Not to Judge: Can Large Language Models Leverage the Dispute Focus in Legal Judgment?
Evaluating Answer Leakage Robustness of LLM Tutors against Adversarial Student Attacks
ArgGenBench: Benchmarking the Complex Controlled Argument Generation Capability of Large Language Models
Language-Aware Token Boosting: LLM Language Confusion Reduction Without Tuning
HEALing Entropy Collapse: Enhancing Exploration in Few-Shot RLVR via Hybrid-Domain Entropy Dynamics Alignment
Do LLMs Encode Functional Importance of Reasoning Tokens ?
EA-Agent: A Structured Multi-Step Reasoning Agent for Entity Alignment
The “Knowledge–Behavior Gap” in Cultural Taboo Safety of Large Language Models
UMPIRE: Unveiling LLM-generated Posts via Redundant Expressions
Attribution, Citation, and Quotation: A Survey of Evidence-based Text Generation with Large Language Models
MirrorCAPTCHA: Wild CAPTCHA, Wild Distribution, Wild Web-based Platform Meet Multimodal LLM Agents
GASE: Graph-Aware Semantic Embedding Learning with Frozen LLMs for Text-Attributed Graphs
Compositional Steering of Large Language Models with Steering Tokens
Pref-CTRL: Preference Driven LLM Alignment using Representation Editing
Verify Before You Commit: Towards Faithful Reasoning in LLM Agents via Self-Auditing
GiLT: Augmenting Transformer Language Models with Dependency Graphs
TAMAS: Benchmarking Adversarial Risks in Multi-Agent LLM Systems
How Controllable Are Large Language Models? A Unified Evaluation across Behavioral Granularities
Scaling Behaviors of LLM Reinforcement Learning Post-Training: An Empirical Study in Mathematical Reasoning
A Survey of Inductive Reasoning for Large Language Models
CogToM: A Comprehensive Theory of Mind Benchmark inspired by Human Cognition for Large Language Models
VecInfer: Efficient LLM Inference with Low-Bit KV Cache via Outlier-Suppressed Vector Quantization
SAFO: Stable Adaptive Fairness Optimization for LLM-Based Social Survey Simulation
Enhancing LLM-based Search Agents via Contribution Weighted Group Relative Policy Optimization
Optimizing User Profiles via Contextual Bandits for Retrieval-Augmented LLM Personalization
Understanding LLM Performance Degradation in Multi-Instance Processing: The Roles of Instance Count and Context Length
Do LLMs Know Tool Irrelevance? Demystifying Structural Alignment Bias in Tool Invocations
LLM-Generated Text May Harm Your Retrieval! A Robust Detection Strategy for Retrieval-Augmented Generation
The Retrieval Bottleneck: Scaling Laws for Reinforcement Learning in RAG
Why Do LLM-based Web Agents Fail? A Hierarchical Planning Perspective
Backdoors in RLVR: Jailbreak Backdoors in LLMs From Verifiable Reward
Label Effects: Shared Heuristic Reliance in Trust Assessment by Humans and LLM-as-a-Judge
Self-SoftCoT: A Self-Consistent Framework via Position-Aware Latent Space Reinforcement Learning
Routing with Generated Data: Annotation-Free LLM Skill Estimation and Expert Selection
Injecting Context via Situation Working Memory for Logical Reasoning with LLMs
ProMed: Shapley Information Gain Guided Reinforcement Learning for Proactive Medical LLMs
SafeAgent: Safeguarding LLM Agents via an Automated Risk Simulator
Alexandria: A Multi-Domain Dialectal Arabic Machine Translation Dataset for Culturally Inclusive and Linguistically Diverse LLMs
How Much Would a Clinician Edit This Draft? Evaluating LLM Alignment for Patient Message Response Drafting
MetaBench: A Multi-task Benchmark for Assessing LLMs in Metabolomics
MTA: Multi-Granular Trajectory Alignment for Large Language Model Distillation
Measuring Distribution Shift in User Prompts and Its Effects on LLM Performance
TALAS: Teacher-Anchored Layer Alignment with Adaptive Sharpness-Aware Minimization for Embedding Distillation
The Personalization Trap: How User Memory Alters Emotional Reasoning in LLMs
Multimodal Large Language Models for Multi-Subject In-Context Image Generation
Discourse Realization of Generics in Human and LLM-generated Texts
SRA: Span Representation Alignment for Large Language Model Distillation
Neuron-Aware Active Few-Shot Learning for LLMs
Rethinking Expert Trajectory Utilization in LLM Post-training for Mathematical Reasoning
LoPT: Lossless Parallel Tokenization Acceleration for Long Context Inference of Large Language Model
RedCoder: Automated Multi-Turn Red Teaming for Code LLMs
Scaling Test-Time Compute to Achieve IOI Gold Medal with Open-Weight Models
PIArena: A Platform for Prompt Injection Evaluation
ChemReason-Bench: Benchmarking Large Language Models for Procedural Reasoning in Experimental Chemistry
How Instruction and Reasoning Data shape Post-Training: Data Quality through the Lens of Layer-wise Gradients
MARS²: Scaling Multi-Agent Tree Search via Reinforcement Learning for Code Generation
Ranking Reasoning LLMs under Test-Time Scaling
PRISM: Probing Reasoning, Instruction, and Source Memory in LLM Hallucinations
ChiKhaPo: A Large-Scale Multilingual Benchmark for Evaluating Lexical Comprehension and Generation in Large Language Models
On the Rejection Criterion for Proxy-based Test-time Alignment
Beyond Code Pairs: Dialogue-Based Data Generation for LLM Code Translation
IterCOMP: Reasoning-aware Adaptive Prompt Compression for Multi-hop Question Answering
Do LLMs Really Memorize Personally Identifiable Information? Revisiting PII Leakage with a Cue-Controlled Memorization Framework
Observations and Remedies for Large Language Model Bias in Self-Consuming Performative Loop
LLM-Based Multi-Task Bangla Hate Speech Detection: Type, Severity, and Target
CURA: Clinical Uncertainty Risk Alignment for Language Model–Based Risk Prediction
EthicMind: A Risk-Aware Framework for Ethical-Emotional Alignment in Multi-Turn Dialogue
Resolving the Security-Auditability Dilemma with Auditable Latent Chain-of-Thought Alignment
ART: Attention Replacement Technique to Improve Factuality in LLMs
More Thinking, Less Talking: Internalizing Deliberative Safety into LLM Parameters
ToolScope: Enhancing LLM Agent Tool Use through Tool Merging and Context-Aware Filtering
Conjunctive Prompt Attacks in Multi-Agent LLM Systems
Revisiting Audio-language Pretraining for Learning General-purpose Audio Representation
Trajectory Signatures of Deception in Large Language Models
Improving the Distributional Alignment of LLMs using Supervision
Experiments or Outcomes? Probing Scientific Feasibility in Large Language Models
SMARTER: A Data-efficient Framework to Improve Toxicity Detection with Explanation via Self-augmenting Large Language Models
Training LLMs for Divide-and-Conquer Reasoning Elevates Test-Time Scalability
What Makes a Good Curriculum? Disentangling the Effects of Data Ordering on LLM Mathematical Reasoning
Confident, Calibrated, or Complicit: Safety Alignment and Ideological Bias in LLM Hate Speech Detection
Aligning Large Language Models via Fully Self-Synthetic Data
GAM: Hierarchical Graph-based Agentic Memory for LLM Agents
CypherSmith: Transforming Text-to-Cypher Generation for LLMs with Synthetic Data
New Terms, New Toxicity: Consensus-based Chinese Neologism Toxicity Detection via Search-Augmented LLMs
L2Dir: Integrating L₂-Norm and Directional Alignment for Unsupervised Contrastive Representation Learning in Multimodal Retrieval
Towards Intrinsic Interpretability of Large Language Models: A Survey of Design Principles and Architectures
What Deserves Memory: Adaptive Memory Distillation for LLM Agents
MoRI: Learning Motivation-Grounded Reasoning for Scientific Ideation in Large Language Models
CaBSALLM: Efficient Context-Aware Batch Annotation of Conversational Streams with Large Language Models
WSDPO: A Generative Word Sense Disambiguation Framework with Chain-of-Thought and Preference Optimization
Lizard: An Efficient Linearization Framework for Large Language Models
S2S-Arena: Evaluating Paralinguistic Instruction Following in Speech-to-Speech Models
Can LLM Safety Be Ensured by Constraining Parameter Regions?
CityVG: Contrastive Fine-Tuning and Reward-Based Chain-of-Thought Reasoning for Zero-Shot City-Scale 3D Visual Grounding
E2EDev: Benchmarking Large Language Models in End-to-End Software Development Task
Reasoning While Asking: Transforming Reasoning Large Language Models from Passive Solvers to Proactive Inquirers
Mitigating Selection Bias in Large Language Models via Permutation-Aware GRPO
KG-ViP: Bridging Knowledge Grounding and Visual Perception in Multi-modal LLMs for Visual Question Answering
Business as Rulesual: A Benchmark and Framework for Business Rule Flow Modeling with LLMs
LeLoRA: Learnable Low-Rank Adaptation of Large Language Models
Gated Tree Cross-Attention for Checkpoint-Compatible Syntax Injection in Decoder-Only LLMs
Octopus: Gated Selective Attention for Memory-Bounded Long-Context Inference in Large Language Models
Escaping the Echo Trap: On Credit Assignment Failure in Multi-turn LLM Self-Reflection
ARF-RLHF: Adaptive Reward-Following for RLHF through Emotion-Driven Self-Supervision and Trace-Biased Dynamic Optimization
SMART: Evaluating LLMs’ Mathematical Reasoning via a Human Cognitive Process-Inspired Benchmark
LBLLM: Lightweight Binarization of Large Language Models via Three-Stage Distillation
SeDev: Structured Semantic Exploration for LLM-Driven Code Generation
User Perceptions vs. Proxy LLM Judges: Privacy and Helpfulness in LLM Responses to Privacy-Sensitive Scenarios
ShopSimulator: Evaluating and Exploring RL-Driven LLM Agent for Shopping Assistants
NL → Schedule: Evaluate Multitask Scheduling Capability of Large Language Models
SLICEFORMER: Static Program Slicing Using Language Models With Dataflow-Aware Pretraining and Constrained Decoding
SCOPE: Boosting LLM Efficiency with Scoped Position Encoding
Debate-of-Thoughts: Resolving Knowledge Conflicts in LLMs Through Internal Deliberation
Projecting Out the Malice: A Global Subspace Approach to LLM Detoxification
From Local to Global: Revisiting Structured Pruning Paradigms for Large Language Models
GenomeQA: Benchmarking General Large Language Models for Genome Sequence Understanding
If an LLM Were a Character, Would It Know Its Own Story? Evaluating Lifelong Learning in LLMs
Graph Reasoning Paradigm: Structured and Symbolic Reasoning with Topology-Aware Reinforcement Learning for Large Language Models
LLM-Powered Benchmark Factory: Reliable, Generic, and Efficient
Attn-GS: Attention-Guided Context Compression for Efficient Personalized LLMs
Structured Semantic Information Helps Retrieve Better Examples for In-Context Learning Applied to Few-Shot Relation Extraction
DUD: Decoupled Update Dynamics for Reliable Uncertainty Quantification in Large Language Models
METER: Evaluating Multi-Level Contextual Causal Reasoning in Large Language Models
PersonalAlign: Hierarchical Implicit Intent Alignment for Personalized GUI Agent with Long-Term User-Centric Records
“Excuse me, may I say something…” CoLabScience, A Proactive AI Assistant for Biomedical Discovery and LLM-Expert Collaborations
PICTURE: Enhancing Theory-of-Mind in Large Language Models by Revealing, Not Hiding, Characters’ Lack of Knowledge
Memorization, Emergence, and Explaining Reversal Failures: A Controlled Study of Relational Semantics in LLMs
Framing Political Bias in Multilingual LLMs Across Pakistani Languages
InsAT: Instance-aware Semantic Alignment and Transfer from Human–Object Keypoints for Zero-to-Few-shot Action Understanding
Multi-View Attention Multiple-Instance Learning Enhanced by LLM Reasoning for Cognitive Distortion Detection
CʜAIRO: Contextual Hierarchical Analogical Induction and Reasoning Optimization for LLMs
How Context Shapes Truth: Geometric Transformations of Statement-level Truth Representations in LLMs
Reasoning Hijacking: The Fragility of Reasoning Alignment in Large Language Models
The Dominance of Text Space: Unveiling the Asymmetric Nature of Cross-Modal Alignment in Large Language Models
WildFeedback: Aligning LLMs With In-situ User Interactions And Feedback
SSG: Logit-Balanced Vocabulary Partitioning for LLM Watermarking
Joint Knowledge Base Completion and Question Answering by Combining Large Language Models and Small Language Models
The Role of Mixed-Language Documents for Multilingual Large Language Model Pretraining
The Side Effects of Being Smart: Safety Risks in MLLMs’ Multi-Image Reasoning
Action Boundary Blindness: When LLM Agents Cannot Tell Where One Action Ends and Another Begins
ProMedical: Hierarchical Fine-Grained Criteria Modeling for Medical LLM Alignment via Explicit Injection
R2IF: Aligning Reasoning with Decisions via Composite Rewards for Interpretable LLM Function Calling
Frozen LLMs are Native Decoders for High-Norm Semantic Vectors
Glyph: Scaling Context Windows via Visual-Text Compression
TA-GRPO-d: Trajectory-Aware GRPO for Optimizing Denoising Trajectories in Diffusion LLMs
CSRP: Chain-of-Thought Reasoning for Chinese Text Correction via Reinforcement Learning with Efficiency-Aware Rewards
Characterizing the Expressivity of Local Attention in Transformers
Zero-Shot Detection of LLM-Generated Text using Temperature Sensitivity
Revealing Procedural Reasoning Structures in Chain-of-Thought Training via Span-Level Gradient Organization
Social Dynamics as Critical Vulnerabilities that Undermine Objective Decision-Making in LLM Collectives
Mitigating Over-Refusal in Aligned Large Language Models via Inference-Time Activation Energy
Refining and Reusing Annotation Guidelines for LLM Annotation
AlignCultura: Towards Culturally Aligned Large Language Models?
UPDESH: Synthesizing Grounded Instruction Tuning Data for 13 Indic Languages
Dynamic Generation of Multi LLM Agents Communication Topologies with Graph Diffusion Models
TaxPraBen: A Scalable Benchmark for Structured Evaluation of LLMs in Chinese Real-World Tax Practice
Tears or Cheers? Benchmarking LLMs via Culturally Elicited Distinct Affective Responses
Emergent Misalignment via In-Context Learning: Narrow in-context examples can produce broadly misaligned LLMs
EvoRoute: Experience-Driven Self-Routing LLM Agent Systems
Foresight Optimization for Strategic Reasoning in Large Language Models
DetectRL-X: Towards Reliable Multilingual and Real-World LLM-Generated Text Detection
ImmersiveTTS: Environment-Aware Text-to-Speech with Multimodal Diffusion Transformer and Domain-Specific Representation Alignment
CodeRipple: Wavelet-Based Detection of LLM-Generated Code
CoMeT: Collaborative Memory Transformer for Efficient Long Context Modeling
SED-SFT: Selectively Encouraging Diversity in Supervised Fine-Tuning
HumanLLM: Benchmarking and Improving LLM Anthropomorphism via Human Cognitive Patterns
Vision-Language Introspection: Mitigating Overconfident Hallucinations in MLLMs via Interpretable Bi-Causal Steering
Frame-Semantic Knowledge Injection for Event-Level Inference in LLMs
Teaching LLMs Human-Like Editing of Inappropriate Argumentation via Reinforcement Learning
FLAIR: Steering LLM Mathematical Problem Solving based on A Fuzzy-Logic-AssIsted Reasoner
Exploring Cross-Client Memorization of Training Data in Large Language Models for Federated Learning
G-IdiomAlign: A Gloss-Pivoted Benchmark for Cross-Lingual Idiom Alignment
SciCoQA: Quality Assurance for Scientific Paper–Code Alignment
ImpRIF: Stronger Implicit Reasoning Leads to Better Complex Instruction Following
Uncertainty-Aware Routing for Principled Alignment with MoE Dynamics
More Aligned, Less Diverse? Analyzing the Grammar and Lexicon of Two Generations of LLMs
Discovering a Shared Logical Subspace: Steering LLM Logical Reasoning via Alignment of Natural-Language and Symbolic Views
Why Does Reinforcement Learning Generalize? A Feature-Level Mechanistic Study of Post-Training in Large Language Models
Polymorphic Universal Transformer
Can Reasoning Path still be Effective as Input? Bridging Post-Reasoning to Chain-of-Thought Compression
Putting HUMANS first: Efficient LAM Evaluation with Human Preference Alignment
BlindGuard: Safeguarding LLM-based Multi-Agent Systems under Unknown Attacks
Black-Box Membership Inference Attacks for Video Training Data in Multimodal Large Language Models
Please refuse to answer me! Mitigating Over-Refusal in Large Language Models via Adaptive Contrastive Decoding
Knowledge Injection Exists in MoE? Exploring Expert-Aware Contrast Decoding in MoE for Mitigating LLMs’ Hallucinations
Beyond Experience Retrieval: Learning to Generate Utility-Optimized Structured Experience for Frozen LLMs
Zero-shot Large Language Models for Automatic Readability Assessment
Chain-of-Thought as a Lens: Evaluating Structured Reasoning Alignment between Human Preferences and Large Language Models
Robust Membership Inference for Large Language Models under Adversarial Generative Corruption
ASTRA: An Automated Framework for Strategy Discovery, Retrieval, and Evolution for Jailbreaking LLMs
LLM Safety From Within: Detecting Harmful Content with Internal Representations
Evaluating LLMs on Large-Scale Graph Property Estimation via Random Walks
MedEinst: Benchmarking the Einstellung Effect in Medical LLMs through Counterfactual Differential Diagnosis
Global Adaptive Momentum Meets Local Personalized Perturbation: Efficient Federated LLM Fine-Tuning with Zeroth-Order Gradients
Beyond Query Memorization: Large Language Model Routing with Query Decomposition and Historical Matching
Market-Bench: Benchmarking Large Language Models on Economic and Trade Competition
Benchmarking Post-Training Quantization of Large Language Models under Microscaling Floating Point Formats
Too Long, Do Re-weighting for Efficient LLM Reasoning Compression
GroupToM-Bench: Benchmarking Group Theory of Mind and Nonlinear Social Emergence in MLLMs
Assessing the Belief Consistency of Large Language Models on the Logical Conversation Process
Textual Steering Vectors Can Improve Visual Understanding in Multimodal Large Language Models
Learning Uncertainty from Sequential Internal Dispersion in Large Language Models
Revisiting Evaluation of Question Answering Systems in Low-Resource Indic Languages: Bridging Human and Metric Alignment
Quantifying and Mitigating Socially Desirable Responding in LLMs: A Desirability-Matched Graded Forced-Choice Psychometric Study
From Curated Data to Scalable Models: Continual Pre-training of Dense and MoE Large Language Models for Tibetan
UrbanGeoEval: A City-Scale Benchmark for Evaluating Large Language Models in Geospatial Reasoning
Data-efficient Targeted Token-level Preference Optimization for LLM-based Text-to-Speech
GROKE: Vision-Free Navigation Instruction Evaluation via Graph Reasoning on OpenStreetMap
BOSCH: Black-Box Binary Optimization for Short-Context Attention-Head Selection in LLMs
Scaling Reasoning, Losing Control: Evaluating Instruction Following in Large Reasoning Models
MirrorQA: Benchmarking Multimodal LLMs on Mirror-Orientation Reasoning
CAP: Controllable Alignment Prompting for Unlearning in LLMs
Rendering Data Unlearnable by Exploiting LLM Alignment Mechanisms
CAR-bench: Evaluating the Consistency and Limit-Awareness of LLM Agents under Real-World Uncertainty
Tiny Scales, Great Challenges: The Limits of Multimodal LLMs in Scale Recognition
From Selection to Refinement: Iterative Optimization for Instruction Data
Knowledge-to-Verification: Exploring RLVR for LLMs in Knowledge-Intensive Domains
Mem-Gallery: Benchmarking Multimodal Long-Term Conversational Memory for MLLM Agents
HarDBench: A Benchmark for Draft-Based Co-Authoring Jailbreak Attacks for Safe Human–LLM Collaborative Writing
Retrieval-Augmented Defense: Adaptive and Controllable Jailbreak Prevention for Large Language Models
CNSL-bench: Benchmarking the Sign Language Understanding Capabilities of MLLMs on Chinese National Sign Language
Thinking in Schemas: Robust Syllogistic Reasoning in LLMs
GenPT: Beyond Self-Report for Reliable LLM Psychometrics via Generative Projective Testing
Learning to Conceal Risk: Controllable Multi-turn Red Teaming for LLMs in the Financial Domain
Beyond Static Alignment: Adaptive Arbitration for Semantic Incongruence in Semi-Supervised Multimodal Sentiment Analysis
LLM Beliefs Are in Their Heads
One Pair Suffices: Unlocking Universal Zero-Shot Translation via Cross-Architecture Alignment
LASA: Language-Agnostic Semantic Alignment at the Semantic Bottleneck for LLM Safety
Quantifying the Impact of Translation Errors on Multilingual LLM Evaluation
Long-Context Reasoning Through Proxy-Based Chain-of-Thought Tuning
MASPO: Unifying Gradient Utilization, Probability Mass, and Signal Reliability for Robust and Sample-Efficient LLM Reasoning
Survey Response Generation: Generating Closed-Ended Survey Responses In-Silico with Large Language Models
Anchoring the Affective Manifold: Learning Canonical and Disentangled Representations via Generative Cross-Modal Alignment
Incomplete In-context Learning
Fine-tuning vs. In-context Learning in Large Language Models: A Formal Language Learning Perspective
Where Paths Split: Localized, Calibrated Control of Moral Reasoning in Large Language Models
Mechanisms of Prompt-Induced Hallucination in Vision–Language Models
LLM4Cell: Taxonomy and Evaluation of LLM and Agentic Models for Single-Cell Biology
From Nodes to Narratives: Explaining Graph Neural Networks with LLMs and Graph Context
Which Reasoning Trajectories Teach Students to Reason Better? A Simple Metric of Informative Alignment
From Proof to Program: Characterizing Tool-Induced Reasoning Hallucinations in Large Language Models
A BERTology View of LLM Orchestrations: Token- and Layer-Selective Probes for Efficient Single-Pass Classification
Can Large Language Models Keep Up? Benchmarking Online Adaptation to Continual Knowledge Streams
A Survey of Multimodal Mathematical Reasoning: From Perception, Alignment to Reasoning
LLMSurgeon: Diagnosing Data Mixture of Large Language Models
ACBQ: Adaptive Cross-Block Quantization of Large Language Models
SecureGate: Learning When to Reveal PII Safely via Token-Gated Dual-Adapters for Federated LLMs
AdaFuse: Adaptive Ensemble Decoding for Large Language Models
TLPO: Token-Level Policy Optimization for Mitigating Language Confusion in Large Language Models
JW-SVD: Bridging the Cross-Modal Mismatch in Post-Training MLLM Compression
Estimating the Black-box LLM Uncertainty with Distribution-Aligned Adversarial Distillation
CoDial: Interpretable Task-Oriented Dialogue Systems Through Dialogue Flow Alignment
MDP-GRPO: Stabilized Group Relative Policy Optimization for Multi-Constraint Instruction Following
TokenTiming: A Dynamic Alignment Method for Universal Speculative Decoding Model Pairs
Thinking Alignment of Scenario-Oriented User Simulation
AdapShot: Adaptive Many-Shot In-Context Learning with Semantic-Aware KV Cache Reuse
ReActR: Reasoning through Error-Activated Reflection for LLM Post-Training
RL-PLUS: Countering Capability Boundary Collapse of LLMs in Reinforcement Learning with Hybrid-policy Optimization
Explain the Synth: Interpretable Evaluation of LLM Data Synthesis
Beyond the Leaderboard: Rethinking Medical Benchmarks for Large Language Models
HeteroCache: A Dynamic Retrieval Approach to Heterogeneous KV Cache Compression for Long-Context LLM Inference
Sparse-RL: Breaking the Memory Wall in LLM Reinforcement Learning via Stable Sparse Rollouts
Do Morals Guide How LLMs Think? The Role of Ethical Perspectives in General Problem Solving
ViLL-E: Video LLM Embeddings for Retrieval
From Trajectories to Graphs: Contract-Checked Editing for Verifier-Guided LLM Reasoning
EdgeFormer: Latency-Aware Collaborative Multi-Head Attention of Transformer Inference in Edge Networks
FAIRGAMER: Evaluating Social Biases in LLM-Based Video Game NPCs
EVOTOOL: Self-Evolving Tool-Use Policy Optimization in LLM Agents via Blame-Aware Mutation and Diversity-Aware Selection
A Lightweight Explainable Guardrail for Prompt Safety
PodBench: A Comprehensive Benchmark for Instruction-Aware Audio-Oriented Podcast Script Generation
MIND: From Passive Mimicry to Active Reasoning through Capability-Aware Multi-Perspective CoT Distillation
Knowledge Vector of Logical Reasoning in Large Language Models
SMILE-Next: Teaching Large Language Models to Detect, Classify, and Reason about Laughter
Activation Decomposition and Steering for LLM Backdoor Remediation
A Survey of Large Language Models for Text-Guided Molecular Discovery: From Molecule Generation to Optimization
Reward Alignment Optimization: A Direct Point-wise Alignment Approach
Can You Make It Sound Like You? Post-Editing LLM-Generated Text for Personal Style
PPA-Plan: Proactive Pitfall Avoidance for Reliable Planning in Long-Context LLM Reasoning
OPeRA: A Dataset of Observation, Persona, Rationale, and Action for Evaluating LLMs on Human Online Shopping Behavior Simulation
Can LLM Agents Simulate Multi-Turn Human Behavior? Evidence from Real Online Customer Behavior Data
Lost in Execution: On the Multilingual Robustness of Tool Calling in Large Language Models
MTA:A Merge-then-Adapt Framework for Personalized Large Language Models
Investigating Counterfactual Unfairness in LLMs towards Identities through Humor
Nature-Inspired Population-Based Evolution of Large Language Models
MTRouter: Cost-Aware Multi-Turn LLM Routing with History–Model Joint Embeddings
ParaSuite: Boosting LLM Reasoning via Paradox Resolution
ReTRE: Benchmarking LLM Transfer Robustness with Structure-Preserving Variants
Do MLLMs Capture How Interfaces Guide User Behavior? A Benchmark for Multimodal UI/UX Design Understanding
DarwinTOD: LLM-Driven Lifelong Self-evolution for Task-oriented Dialog Systems
Route to Rome Attack: Directing LLM Routers to Expensive Models via Adversarial Suffix Optimization
Understanding the Prompt Sensitivity
rSIM: Incentivizing Reasoning Capabilities of LLMs via Reinforced Strategy Injection
SafeConstellations: Mitigating Over-Refusals in LLMs Through Task-Aware Representation Steering
AIPO: Adaptive Information Guided Token-Level Reinforcement Learning for Large Language Model Reasoning
AgentGym2: Benchmarking Large Language Model Agents in De-Idealized Real-World Environments
INFACT: A Diagnostic Benchmark for Induced Faithfulness and Factuality Hallucinations in Video-LLMs
CLAOCS-TX: Cross-Lingual Triplet Extraction with Aspect-Opinion-Aware Code-Switched Prompting and LLM-Guided Contrastive Distillation
When Does Language Matter? Multilingual Instructions Reveal Step-wise Language Sensitivity in Vision-Language-Action Models
DialDefer: A Framework for Detecting and Mitigating LLM Dialogic Deference
Parallel Test-Time Scaling for Latent Reasoning Models
When Benchmarks Leak: Inference-Time Decontamination for LLMs
HSGraphAgent: Knowledge-Graph-Guided Large Language Models for Harmonized System Code Classification
Truth as a Trajectory: What Internal Representations Reveal About Large Language Model Reasoning
TInR: Exploring Tool-Internalized Reasoning in Large Language Models
One Persona, Many Cues, Different Results: How Sociodemographic Cues Impact LLM Personalization
Lost in the Mix: Evaluating LLM Understanding of Code-Switched Text
Building LLMs Like LEGO: Two-dimensional Architecture Reassembly of Large Language Models
How Long Reasoning Chains Influence LLMs’ Judgment of Answer Factuality
Revealing the Seen, Imagining the Beyond: A Survey of Image-Grounded Chain-of-Thought Reasoning in Multimodal LLMs
Layer-Wise High-Impact Parameter Ratio Optimization in Post-Training Quantization for Large Language Models
TwiUSD: A Benchmark Dataset and Structure-Aware LLM Framework for User Stance Detection
Render-of-Thought: Rendering Textual Chain-of-Thought as Images for Visual Latent Reasoning
SHARP: Self-adaptive Harmful Category-aware Prompt Generation for Black-box Jailbreaking
Unveiling the Limits of Large Language Models in Inferring Pragmatic Meaning from Non-Verbal Responses
Cross-Prompt Automated Essay Scoring of Multiple Traits: Making Sense of the State of the Art
A Linguistics-Aware LLM Watermarking via Syntactic Predictability
SciCustom: A Framework for Custom Evaluation of Scientific Capabilities in Large Language Models
Multi-Task Representation Alignment on Language Understanding: A Mutual Information Perspective
EconProver: Towards More Economical Test-Time Scaling for Automated Theorem Proving
LLM-Based Multi-Agent Systems for Clinical Workflows: A Survey of AI Hospitals
Mind’s Eye: A Benchmark of Visual Abstraction, Transformation and Composition for Multimodal LLMs
When High Accuracy Hides Poor Calibration: Rethinking Confidence Evaluation in Transformer-Based Text Classification with Balanced Brier Score
Privacy-R1: Privacy-Aware Multi-LLM Agent Collaboration via Reinforcement Learning
Reinforcement Learning for Diffusion LLMs via Energy-Based Gibbs Alignment
From Recognition to Reasoning: Benchmarking and Enhancing MLLMs on Real-World Receipt Document Understanding
Mind the Pause: Disfluency-Aware Objective Tuning for Multilingual Speech Correction with LLMs
BioTool: A Comprehensive Tool-Calling Dataset for Enhancing Biomedical Capabilities of Large Language Models
COMPASS: A Framework for Evaluating Organization-Specific Policy Alignment in LLMs
Dual Alignment Between Language Model Layers and Human Sentence Processing
FactCorrector: A Graph-Inspired Approach to Long-Form Factuality Correction of Large Language Models
Decoupling Generalization and Adaptation in Meta-Learning for Large Language Models
DPEPO: Diverse Parallel Exploration Policy Optimization for LLM-based Agents
ReGATE: Learning Faster and Better with Fewer Tokens in MLLMs
From Words to Pixels: A Comprehensive Survey on Large Language Models in Visual Segmentation
Red-Bandit: Test-Time Adaptation for LLM Red-Teaming via Bandit-Guided LoRA Experts
Graph-Based Alternatives to LLMs for Human Simulation
GrAInS: Gradient-based Attribution for Inference-Time Steering of LLMs and VLMs
OLA: Output Language Alignment in Code-Switched LLM Interactions
Reasoning Is Not All You Need: Examining LLMs for Multi-Turn Mental Health Conversations
BatonVoice: An Operationalist Framework for Enhancing Controllable Speech Synthesis with Linguistic Intelligence from LLMs
Monotonic Scaffolding as a Diagnostic Lens for Legal Reasoning in LLMs
Jailbreak-Zero: A Path to Pareto Optimal Red Teaming for Large Language Models
Chain-of-Thought Degrades Visual Spatial Reasoning Capabilities of Multimodal LLMs
Factual Retrieval in LLMs Is a Redundant, Distributed and Non-Contiguous Process
What About the Scene With the Hitler Reference? HAUNT: A Framework to Probe LLMs’ Self-consistency in Closed Domains Via Adversarial Nudge
Knowledge without Wisdom: Measuring Misalignment between LLMs and Intended Impact
Apertus: Democratizing Open and Compliant LLMs for Global Language Environments
Adaptive Instruction Composition for Automated LLM Red-Teaming
CHOIR: Harmonizing Structured Persona Diversity for Robust Collaborative LLM Reasoning
Revisiting Non-Verbatim Memorization in Large Language Models: The Role of Entity Surface Forms
ChatAnime: Towards User-Centered Emotional Support in LLM-based Virtual Character Chat
SciPedia: Unlocking the Value of Scientific Data for Pre-training
Self-Guided Alignment: Adaptive Preference Sensing for Multi-Objective Generation
ReasMark: A Robust Watermark for Attributing LLM Reasoning Under Knowledge Distillation Attacks
Characterizing and Evaluating Working Emotion Vocabularies in Multilingual Large Language Models
Solve-Detect-Verify: Inference-Time Scaling with Flexible Generative Verifier
SPARD: Self-Paced Curriculum for RL Alignment via Integrating Reward Dynamics and Data Utility
Lost in Simulation: LLM-Simulated Users are Unreliable Proxies for Human Users in Agentic Evaluations
Toward Robust Evaluation for Multilingual Grammatical Error Correction: Can Large Language Models Replace Human References?
KARL: Reinforcement Learning for LLM Agents on Multi-Turn Knowledge-Intensive Agentic Tasks
TokDrift: When LLM Speaks in Subwords but Code Speaks in Grammar
REVEALER: Reinforcement-Guided Visual Reasoning for Element-Level Text-Image Alignment Evaluation
Do LLM Agents Mirror Socio-Cognitive Effects in Power-Asymmetric Conversations?
Preference Heads in Large Language Models: A Mechanistic Framework for Interpretable Personalization
Influence-based Online Experience Selection for Effective RLHF
SharVeT: Similarity-aware Parameter Sharing with Vector-based Tuning for Efficient LLM Compression
Beyond Variance: Knowledge-Aware LLM Compression via Fisher-Aligned Subspace Diagnostics
REMIND: Memorization and Unlearning in LLMs Through the Lens of Input Loss Landscapes
Is Chain-of-Thought Really Not Explainability? Chain-of-Thought Can Be Faithful without Hint Verbalization
SELECting over Tokens: Curating Pre-training Data at Scale via Token Classification
TROJail: Trajectory-Level Optimization for Multi-Turn Large Language Model Jailbreaks with Process Rewards
Constructing coherent spatial memory in LLM agents through graph rectification
JurisBench: A Deep Benchmark for Assessing Large Language Models in Professional Legal Practice
River-LLM: Large Language Model Seamless Exit Based on KV Share