R
Published on

ICLR 2026 — Natural Language Processing

Natural Language Processing

59 papers (0 oral)

LongWriter-Zero: Mastering Ultra-Long Text Generation via Reinforcement Learning

CounselBench: A Large-Scale Expert Evaluation and Adversarial Benchmarking of Large Language Models in Mental Health Question Answering

Scalable Multilingual Multimodal Machine Translation with Speech-Text Fusion

40. Taming Polysemanticity in LLMs: Theory-Grounded Feature Recovery via Sparse Autoencoders

  • Topics: LLMs & Foundation Models, Interpretability & Mechanistic Interpretability, Theory & Deep Learning Theory

DAMR: Efficient and Adaptive Context-Aware Knowledge Graph Question Answering with LLM-Guided MCTS

Text2Arch: A Dataset for Generating Scientific Architecture Diagrams from Natural Language Descriptions

A.I.R.: Enabling Adaptive, Iterative, and Reasoning-based Frame Selection For Video Question Answering

Token Alignment Heads: Unveiling Attention's Role in LLM Multilingual Translation

Personalized Feature Translation for Expression Recognition: An Efficient Source-Free Domain Adaptation Method

CellAgent: LLM-Driven Multi-Agent Framework for Natural Language-Based Single-Cell Analysis

Synthesizing High-Quality Visual Question Answering from Medical Documents with Generator-Verifier LMMs

A Structured, Tagged, and Localized Visual Question Answering Dataset with Full Sentence Answers and Scene Graphs for Chest X-ray Images

MAD-Logic: Multi-Agent Debate Enhances Symbolic Translation and Reasoning

Reliable Fine-Grained Evaluation of Natural Language Math Proofs

Improving Attributed Long-form Question Answering with Intent Awareness

LatentQA: Teaching LLMs to Decode Activations Into Natural Language

From Utterance to Vividity: Training Expressive Subtitle Translation LLM via Adaptive Local Preference Optimization

DiscoX: Benchmarking Discourse-Level Translation in Expert Domains

FlexiVoice: Enabling Flexible Style Control in Zero-Shot TTS with Natural Language Instructions

ProofBridge: Auto-Formalization of Natural Language Proofs in Lean via Joint Embeddings

Meta-Adaptive Prompt Distillation for Few-Shot Visual Question Answering

Grounding or Guessing? Visual Signals for Detecting Hallucinations in Sign Language Translation

MoL: Adaptive Mixture-of-Length Reasoning for Efficient Question Answering with Context

TripleSumm: Adaptive Triple-Modality Fusion for Video Summarization

Query-Guided Spatial–Temporal–Frequency Interaction for Music Audio–Visual Question Answering

VERIFY: A Novel Multi-Domain Dataset Grounding LTL in Contextual Natural Language via Provable Intermediate Logic

Learning to Summarize by Learning to Quiz: Adversarial Agentic Collaboration for Long Document Summarization

UniSS: Unified Expressive Speech-to-Speech Translation with Your Voice

Addressing Pitfalls in the Evaluation of Uncertainty Estimation Methods for Natural Language Generation

Text summarization via global structure awareness

Retrospective Sparse Attention for Efficient Long-Context Generation

Topology of Reasoning: Retrieved Cell Complex-Augmented Generation for Textual Graph Question Answering

What's the plan? Metrics for implicit planning in LLMs and their application to rhyme generation and question answering

FrugalRAG: Less is More in RL Finetuning for Multi-hop Question Answering

Enhancing LLMs for Knowledge Base Question Answering by Chain-of-Decomposition

CogniLoad: A Synthetic Natural Language Reasoning Benchmark With Tunable Length, Intrinsic Difficulty, and Distractor Density

Adaptive Domain Shift in Diffusion Models for Cross-Modality Image Translation

MedAraBench: Large-scale Arabic Medical Question Answering Dataset and Benchmark

Human Uncertainty-Aware Data Selection and Automatic Labeling in Visual Question Answering

Logit‑KL Flow Matching: Non‑Autoregressive Text Generation via Sampling‑Hybrid Inference

Universal Multi-Domain Translation via Diffusion Routers

SC-Arena: A Natural Language Benchmark for Single-Cell Reasoning with Knowledge-Augmented Evaluation

QuRL: Rubrics As Judge For Open-Ended Question Answering

Text2Grad: Reinforcement Learning from Natural Language Feedback

Mathesis: Towards Formal Theorem Proving from Natural Languages

A2^2Search: Ambiguity-Aware Question Answering with Reinforcement Learning

LiveWeb-IE: A Benchmark For Online Web Information Extraction

Beyond Markovian Drifts: Action-Biased Geometric Walks with Memory for Personalized Summarization

Natural Language PDDL (NL-PDDL) for Open-world Goal-oriented Commonsense Regression Planning in Embodied AI

Knowledge Exchange with Confidence: Cost-Effective LLM Integration for Reliable and Efficient Visual Question Answering

FS-DFM: Fast and Accurate Long Text Generation with Few-Step Diffusion Language Models

Secret-Protected Evolution for Differentially Private Synthetic Text Generation

Gumbel Distillation for Parallel Text Generation

Tight Bounds for Schrodinger Potential Estimation in Unpaired Data Translation

RobotArena ∞\infty: Scalable Robot Benchmarking via Real-to-Sim Translation

Learning to Orchestrate Agents in Natural Language with the Conductor

A High Quality Dataset and Reliable Evaluation for Interleaved Image-Text Generation

jqBench: a benchmark for reading and editing JSON from natural language and/or examples