ACL 2026 — Generation & Summarization | Rajat Kanti Bhattacharjee

Generation & Summarization

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

No Reader Left Behind: Multi-Agent Summaries Everyone Can Understand
EASE: Entity-Aware Sub-table Generation for Real-world Multi-table QA
Parallel Universes, Parallel Languages: A Comprehensive Study on LLM-based Multilingual Counterfactual Example Generation
PosterForest: Hierarchical Multi-Agent Collaboration for Scientific Poster Generation
FastV-RAG: Towards Fast and Fine-Grained Video QA with Retrieval-Augmented Generation
ReasonEmbed: Enhanced Text Embeddings for Reasoning-Intensive Document Retrieval
ControlAudio: Tackling Text-Guided, Timing-Indicated and Intelligible Audio Generation via Progressive Diffusion Modeling
Contextual Relevance and Adaptive Sampling for LLM-Based Document Reranking
MORPHOGEN: A Multilingual Benchmark for Evaluating Gender-Aware Morphological Generation
CodeHacker: Automated Test Case Generation for Detecting Vulnerabilities in Competitive Programming Solutions
SDE-SQL: Enhancing Text-to-SQL Generation in Large Language Models via Self-Driven Exploration with SQL Probes
BracketRank: Large Language Model Document Ranking via Reasoning-based Competitive Elimination
A Comprehensive Survey of Process Reward Models: Data Generation, Model Construction, and Usage
CODERL+: Improving Code Generation via Reinforcement with Execution Semantics Alignment
Saber: Efficient Sampling with Adaptive Acceleration and Backtracking Enhanced Remasking for Diffusion Language Model in Code Generation
APPSI-139: A Parallel Corpus of English Application Privacy Policy Summarization and Interpretation
Bringing Real-World Relations into Video Generation with Graph-Structured Knowledge
SAGE: Sparse Adaptive Guidance for Dependency-Aware Tabular Data Generation
UniversalRAG: Retrieval-Augmented Generation over Corpora of Diverse Modalities and Granularities
Looking at Radiology Report Generation through a Causal Lens: A Survey
Disco-RAG: Discourse-Aware Retrieval-Augmented Generation
Guaranteeing Knowledge Integration with Joint Decoding for Retrieval-Augmented Generation
Retrieval as Generation: A Unified Framework with Self-Triggered Information Planning
CodeFlowBench: A Multi-turn, Iterative Benchmark for Complex Code Generation
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
AgentOCR: Reimagining Agent History via Optical Self-Compression
A Theoretically Grounded Approach to Summarizing Conversation Dynamics for Forecasting the Derailment of Online Conversations
LogicPoison: Logical Attacks on Graph Retrieval-Augmented Generation
Compete to Complete: Co-opetition Adversarial Learning for Retrieval-Augmented Generation
What Does LLM Refinement Actually Improve? A Systematic Study on Document-Level Literary Translation
Measuring Human Contribution in AI-Assisted Content Generation
ACE-Router: Generalizing History-Aware Routing from MCP Tools to the Agent Web
UNIKIE-BENCH: Benchmarking Large Multimodal Models for Key Information Extraction in Visual Documents
StealthGraph: Exposing Domain-Specific Risks in LLMs through Knowledge-Graph-Guided Harmful Prompt Generation
Efficient Self-Evaluation for Diffusion Language Models via Sequence Regeneration
Don’t Be Misled by Style: A Style-Adaptive Reranker for Capturing Effective Knowledge in Retrieval-Augmented Generation
In-depth Research Impact Summarization through Fine-Grained Temporal Citation Analysis
Is a Document Educational or Just Wikipedia-Style? — Pitfalls of Classifier-Based Quality Filtering
STEM: Structure-Tracing Evidence Mining for Knowledge Graphs-Driven Retrieval-Augmented Generation
Arg-LLaDA: Argument Summarization via Large Language Diffusion Models and Sufficiency-Aware Refinement
arXiv2Table: Toward Realistic Benchmarking and Evaluation for LLM-Based Literature-Review Table Generation
iTAG: Inverse Design for Natural Text Generation with Accurate Causal Graph Annotations
LiGen: Active Lipid Generation via a Molecular Language Model
Investigating More Explainable and Partition-Free Compositionality Estimation for LLMs: A Rule-Generation Perspective
UniMoE-Audio: Unified Speech and Music Generation with Dynamic-Capacity Mixture-of-Experts
KCVR: Knowledge-Centric Video Reconstruction for Structured Pedagogical Summarization via Dynamic Graph Planning
RepoGenesis: Benchmarking End-to-End Microservice Generation from Readme to Repository
AGSC: Adaptive Granularity and Semantic Clustering for Uncertainty Quantification in Long-text Generation
TRACE: Traversal Retrieval-Augmented Chain of Evidence for Document Understanding
Self-Reflective Generation at Test Time
From Past To Path: Masked History Learning for Next-Item Prediction in Generative Recommendation
Unified Thinker: A General Reasoning Core for Image Generation
Visual and Memory–Augmented Soccer Commentary Generation
Memory-Augmented LLM-based Multi-Agent System for Automated Feature Generation on Tabular Data
Improving Retrieval-Augmented Generation without Taxonomy-based Error Categorization
WebCoderBench: Benchmarking Web Application Generation with Comprehensive and Interpretable Evaluation Metrics
EvoNarrator: Modeling Scientific Evolution for Feasible Hypothesis Generation
LLM-SLM Collaborative Framework of Idiomatic Expression Generation
Author-in-the-Loop Response Generation and Evaluation: Integrating Author Expertise and Intent in Responses to Peer Review
Deriving Character Logic from Storyline as Codified Decision Trees
SegTune: Structured and Fine-Grained Control for Song Generation
IUQ: Interrogative Uncertainty Quantification for Long-Form Large Language Model Generation
ALDEN: Reinforcement Learning for Active Navigation and Evidence Gathering in Long Documents
Reinforced Informativeness Optimization for Long-Form Retrieval-Augmented Generation
Illusions of the Gold Standard: A Large-scale Analysis of Human Evaluation Protocols for Long-form Text Generation
Iterative Dual-Model Alignment for Story Evaluation
ReFEree: Reference-Free and Fine-Grained Method for Evaluating Factual Consistency in Real-World Code Summarization
MeanAudio: Fast and Faithful Text-to-Audio Generation with Mean Flows
ModeX: Evaluator-Free Best-of-N Selection for Open-Ended Generation
FormulaSPIN: Self-Play Fine-Tuning for Natural Language to Spreadsheet Formula Generation
SARA: Selective and Adaptive Retrieval-augmented Generation with Context Compression
SlideAgent: Hierarchical Agentic Framework for Multi-Page Visual Document Understanding
LAD-RAG: Layout-aware Dynamic RAG for Visually-Rich Document Understanding
ParaCodex: A Profiling-Guided Autonomous Coding Agent for Reliable Parallel Code Generation and Translation
MARCH: Multi-Agent Radiology Clinical Hierarchy for CT Report Generation
Biomedical Question Answering via Multi-Level Summarization on a Local Knowledge Graph
Narrative License and Model Sycophancy in LLM Summaries of Scientific Work
ViDoRe V3: A Comprehensive Evaluation of Retrieval Augmented Generation in Complex Real-World Scenarios
Decoupling Task-Solving and Output Formatting in LLM Generation
Analyzing and Internalizing Complex Policy Documents for LLM Agents
Anchor: Branch-Point Data Generation for GUI Agents
OpenRubrics: Towards Scalable Synthetic Rubric Generation for Reward Modeling and LLM Alignment
LENS: LLM-Enabled Narrative Synthesis for Mental Health by Aligning Multimodal Sensing with Language Models
Controlling Distributional Bias in Multi-Round LLM Generation via KL-Optimized Fine-Tuning
SciFlow-Bench: Evaluating Structure-Aware Scientific Diagram Generation via Inverse Parsing
LCR-RAG: Enhancing Logical Consistency in Retrieval-Augmented Generation via Neuro-symbolic Reinforcement Learning
HiKEY: Hierarchical Multimodal Retrieval for Open-Domain Document Question Answering
Your Reasoning Benchmark May Not Test Reasoning: Revealing Perception Bottleneck in Abstract Reasoning Benchmarks
Beyond Chunking: Discourse-Aware Hierarchical Retrieval for Long Document Question Answering
GBV-SQL: Guided Generation and SQL2Text Back-Translation Validation for Multi-Agent Text2SQL
Adaptive Planning for Multi-Attribute Controllable Summarization with Monte Carlo Tree Search
Difficulty-Controllable Cloze Question Distractor Generation
REG: Retrieval via Emotion Similarity for Guiding Empathetic Dialogue Generation
DisCo_Speech: Controllable Zero-Shot Speech Generation with A Disentangled Speech Codec
Know the Known and the Unknown: Reasonable Answer Generation with Knowledge-Informed Citations
Suggest-Verify-Revise: A Three-Stage Document-Level Event Causality Identification with Narrative Consistency
StoryCoder: Narrative Reformulation for Structured Reasoning in LLM Code Generation
Discourse Coherence and Response-Guided Context Rewriting for Multi-Party Dialogue Generation
EvolvR: Self-Evolving Pairwise Reasoning for Story Evaluation to Enhance Generation
Identity-Robust Language Model Generation via Content Integrity Preservation
Knowledge Poisoning Attacks on Medical Multi-Modal Retrieval-Augmented Generation
When Bigger Isn’t Better: A Comprehensive Fairness Evaluation of Political Bias in Multi-News Summarisation
CAML: A Conflict-Aware Molecular Language Model Merging Framework for Multi-Constraint Molecular Generation
HiGoE: Hierarchical Graph of Evidence to Enhance Retrieval-Augmented Generation for Long-context Summarization
Region-Grounded Report Generation for 3D Medical Imaging: A Fine-Grained Dataset and Graph-Enhanced Framework
DeepGuard: Secure Code Generation via Multi-Layer Semantic Aggregation
IS-CoT: Breaking the Long-form Generation Collapse via Interleaved Structural Thinking
MTAVG-Bench: A Diagnostic Benchmark for Multi-Talker Dialogue-Centric Audio-Video Generation
Preconditioned Test-Time Adaptation for Out-of-Distribution Debiasing in Narrative Generation
Bridging Internal Consistency and External Alignment: A Causal and Dynamic Interpretability Framework for LLM Generation
R^3AG: Retriever Routing for Retrieval-Augmented Generation
ClusterRAG: Cluster-Based Collaborative Filtering for Personalized Retrieval-Augmented Generation
Aligned Multi-View Scripts for Universal Chart-to-Code Generation
Breaking Block Boundaries: Anchor-based History-stable Decoding for Diffusion Large Language Models
Unveiling the Unknown: Open-Set Entity Typing via Two-Stage Generation
Tailoring Diagnostic Modeling to Individual Learners: Personalized Distractor Generation via MCTS-Guided Reasoning Reconstruction
Efficient Prior-Guided Reasoning for Robust Retrieval-Augmented Generation under Conflicts
LitVISTA: A Benchmark for Narrative Orchestration in Literary Text
MAB-DQA: Addressing Query Aspect Importance in Document Question Answering with Multi-Armed Bandits
FormalScience: Scalable Human-in-the-Loop Autoformalisation of Science with Agentic Code Generation in Lean
BiMol-Diff: A Unified Diffusion Framework for Molecular Generation and Captioning
DEBAR: Mitigating Contextual Bias in Cross-Document Relation Extraction via Dual-Stream Decoupling
LegalChainReasoner: Grounding Criminal Judicial Opinion Generation via Structured Legal Chains
InsideOut: Measuring and Mitigating Insider–Outsider Bias in Interview Script Generation
Attention as Selector: Unlocking VLM Attention for Long Document Page Retrieval
CharTide: Data-Centric Chart-to-Code Generation via Tri-Perspective Tuning and Inquiry-Driven Evolution
Agent Newsroom: Efficient Chronological Report Generation via Dynamic Multi-Agent Collaboration
ChipSeek: Optimizing Verilog Generation via EDA-Integrated Reinforcement Learning
CSPO: Alleviating Reward Ambiguity for Structured Table-to-LaTeX Generation
Chart-MRAG: Benchmarking Multimodal Retrieval Augmented Generation on Chart-based Documents
Revisiting Metric Reliability for Fine-grained Evaluation of Machine Translation and Summarization in Indian Languages
HAG: Hierarchical Demographic Tree-based Agent Generation for Topic-Adaptive Simulation
Stable-RAG: Mitigating Retrieval-Permutation-Induced Hallucinations in Retrieval-Augmented Generation
CIRAG: Construction–Integration Retrieval and Adaptive Generation for Multi-hop Question Answering
Dynamic Infilling Anchors for Format-Constrained Generation in Diffusion Large Language Models
Think Parallax: Solving Multi-Hop Problems via Multi-View Knowledge-Graph-Based Retrieval-Augmented Generation
DocLens: A Tool-Augmented Multi-Agent Framework for Long Visual Document Understanding
Attention Weights as an Indicator: Analyzing and Improving Document Utilization in Retrieval-Augmented Generation
LADR: Locality-Aware Dynamic Rescue for Efficient Text-to-Image Generation with Diffusion Large Language Models
A Multi-Agent Framework for Feature-Constrained Difficulty Control in Reading Comprehension Item Generation
FusionFlow: Enabling Deep Structural Exploration for Automated Agentic Workflow Generation
UniSonate: A Unified Model for Speech, Music, and Sound Effect Generation with Text Instructions
HopWeaver: Cross-Document Synthesis of High-Quality and Authentic Multi-Hop Questions
VerilogLAVD: LLM-Aided Pattern Generation for Verilog CWE Detection
Bloom-Eval: A Hierarchical Evaluation Benchmark for Automatic Survey Generation Based on Bloom’s Taxonomy
GenesisFunc: Multi-Agent Data Generation for Accurate and Generalizable Function-Calling
FactVerse: A Benchmark for Factual Consistency in Interleaved Image–Text Generation
Incorporating Temporal Coherence to Cross-Document Event Coreference Resolution
HiChunk: Evaluating and Enhancing Retrieval Augmented Generation with Hierarchical Chunking
PersonalityDBench: A Dataset for Personality Disorders - from Modeling to Controlled Generation
Beyond Explicit Refusals: Soft-Failure Attacks on Retrieval-Augmented Generation
MavenCoder: Competitive Code Generation via Model Adaptive Planning Strategies and Multi-Perspective Verification Enhancement
CPR-RAG: Clinical Prior-Regularized Retrieval for Anatomy-Aware 3D CT Report Generation
ArgGenBench: Benchmarking the Complex Controlled Argument Generation Capability of Large Language Models
OSCBench: Benchmarking Object State Change in Text-to-Video Generation
Attribution, Citation, and Quotation: A Survey of Evidence-based Text Generation with Large Language Models
SwissGov-RSD: A Human-annotated, Cross-lingual Benchmark for Token-level Recognition of Semantic Differences Between Related Documents
RubricHub: A Comprehensive and Highly Discriminative Rubric Dataset via Automated Coarse-to-Fine Generation
Frankentext: Stitching random text fragments into long-form narratives
Decisive: Guiding User Decisions with Optimal Preference Elicitation from Unstructured Documents
Stress Testing Factual Consistency Metrics for Long-Document Summarization
LLM-Generated Text May Harm Your Retrieval! A Robust Detection Strategy for Retrieval-Augmented Generation
EvoSpark: Endogenous Interactive Agent Societies for Unified Long-Horizon Narrative Evolution
HiddenGuard: Fine-Grained Safe Generation with Specialized Representation Router
ThreadSumm: Summarization of Nested Discourse Threads Using Tree of Thoughts
Enhanced Reasoning for Biomedical Document-Level Relation Extraction via a Novel Cascade Language Model Framework
Multimodal Large Language Models for Multi-Subject In-Context Image Generation
Synthetic Data Generation for Training Diversified Commonsense Reasoning Models
MARS²: Scaling Multi-Agent Tree Search via Reinforcement Learning for Code Generation
LoVeC: Reinforcement Learning for Better Verbalized Confidence in Long-Form Generation
Anchoring the Cache: Mitigating Contextual Hallucination in KV-Compressed Long-Context Summarization
Beyond Static Artifacts: An Evolutionary Framework for Synthetic Claim Generation
ChiKhaPo: A Large-Scale Multilingual Benchmark for Evaluating Lexical Comprehension and Generation in Large Language Models
Beyond Code Pairs: Dialogue-Based Data Generation for LLM Code Translation
Fiction Flows: A Replication and Reinterpretation of Narrative Sequentiality
Evaluating Visual Narrative Coherence in Story Visualization via Diversified Storylines
CypherSmith: Transforming Text-to-Cypher Generation for LLMs with Synthetic Data
ATGL: An Adaptive-Threshold Global Loss for Document-level Relation Extraction
Utility-Oriented Visual Evidence Selection for Multimodal Retrieval-Augmented Generation
DefGen-Bench: A Benchmark for Chinese Criminal Defence Opinion Generation in LegalAI
SeDev: Structured Semantic Exploration for LLM-Driven Code Generation
EVM-QuestBench: An Execution-Grounded Benchmark for Natural-Language Transaction Code Generation
TexOCR: Advancing Document OCR Models for Compilable Page-to-LaTeX Reconstruction
If an LLM Were a Character, Would It Know Its Own Story? Evaluating Lifelong Learning in LLMs
Flow-Based Page Unique Semantic Mapping Architecture for Document Visual Question Answering
SWAN: Semantic Watermarking with Abstract Meaning Representation
PaT: Planning-after-Trial for Efficient Test-Time Code Generation
The Role of Mixed-Language Documents for Multilingual Large Language Model Pretraining
ES4R: Speech Encoding Based on Prepositive Affective Modeling for Empathetic Response Generation
IGenBench: Benchmarking the Reliability of Text-to-Infographic Generation
Enhancing Reinforcement Learning for Radiology Report Generation with Evidence-aware Rewards and Self-correcting Preference Learning
Grammar as Control: Modular Language Generation for the Long Tail
LegalGraphRAG: Multi-Agent Graph Retrieval-Augmented Generation for Reliable Legal Reasoning
Omni-I2C: A Holistic Benchmark for High-Fidelity Image-to-Code Generation
AdaDPI: Document-level Translation Adaptive Agent via Dynamic Parametric Internalization
Cross-Examination Framework: A Task-Agnostic Diagnostic for Information Fidelity in Text-to-Text Generation
Dynamic Generation of Multi LLM Agents Communication Topologies with Graph Diffusion Models
One-step Nonautoregressive Natural Language Generation with Shortcut Flow Matching Models
PHOTON: Hierarchical Autoregressive Modeling for Lightspeed and Memory-Efficient Language Generation
More Aligned, Less Diverse? Analyzing the Grammar and Lexicon of Two Generations of LLMs
Structure Guided Retrieval-Augmented Generation for Factual Queries
From Competition to Synergy: Unlocking Reinforcement Learning for Subject-Driven Image Generation
Deep-Reporter: Deep Research for Grounded Multimodal Long-Form Generation
Survey Response Generation: Generating Closed-Ended Survey Responses In-Silico with Large Language Models
Social Story Frames: Contextual Reasoning about Narrative Intent and Reception
From Nodes to Narratives: Explaining Graph Neural Networks with LLMs and Graph Context
RealChart2Code: Bridging the Gap in Real-World Chart-to-Code Generation via Multi-Task Evaluation
HypoEval: Hypothesis-Guided Evaluation for Natural Language Generation
A Structured Clustering Approach for Inducing Media Narratives
Simple Agents, Biased Judges: Efficient Multi-Party Dialogue Generation & The Evaluation Gap
Locate and Explain: Joint Multimodal Emotion Cause Extraction and Summarization in Conversation
ServImage: An Image Generation and Editing Benchmark from Real-world Commercial Imaging Services
PodBench: A Comprehensive Benchmark for Instruction-Aware Audio-Oriented Podcast Script Generation
A Survey of Large Language Models for Text-Guided Molecular Discovery: From Molecule Generation to Optimization
ReCode: Reinforcing Code Generation with Reasoning-Process Rewards
CT-FineBench: A Diagnostic Fidelity Benchmark for Fine-Grained Evaluation of CT Report Generation
MTRouter: Cost-Aware Multi-Turn LLM Routing with History–Model Joint Embeddings
Automatic and Reliable Evaluation for Academic Caption-to-Figure Generation with LMMs
SciMDR: Advancing Scientific Multimodal Document Reasoning
Learning Faster with Better Tokens: Parameter-Efficient Vocabulary Adaptation for Specialized Text Summarization
SHARP: Self-adaptive Harmful Category-aware Prompt Generation for Black-box Jailbreaking
Mind’s Eye: A Benchmark of Visual Abstraction, Transformation and Composition for Multimodal LLMs
Synthia: Scalable Grounded Persona Generation from Social Media Data
From Recognition to Reasoning: Benchmarking and Enhancing MLLMs on Real-World Receipt Document Understanding
CEBC: Conformal Evidence-Bounded Control for Low-Hallucination Vision–Language Generation
DiNO: Disinformation Narrative Observer
GitChameleon 2.0: Evaluating AI Code Generation Against Python Library Version Incompatibilities
DREAM-S: Speculative Decoding with Searchable Drafting and Target-Aware Refinement for Multimodal Generation
Protein-STORY: Semantic Text-Oriented Representation Yields biologically meaningful Protein embeddings
Self-Guided Alignment: Adaptive Preference Sensing for Multi-Objective Generation
Typology-Aware Multilingual Morphosyntactic Parsing with Joint Abstract Node Modeling
MegaRAG: Multimodal Knowledge Graph-Based Retrieval Augmented Generation