Natural Language Processing

Reasoning Hijacking: The Fragility of Reasoning Alignment in Large Language Models ACL 2026 Reasoning or Knowledge: Stratified Evaluation of Biomedical LLMs EACL 2026 Reasoning’s Razor: Reasoning Improves Accuracy but Hurts Recall at Critical Operating Points in Safety and Hallucination Detection EACL 2026 Reasoning Transfer for an Extremely Low-Resource and Endangered Language: Bridging Languages Through Sample-Efficient Language Understanding AAAI 2026 ReasonRank: Empowering Passage Ranking with Strong Reasoning Ability ACL 2026 Reassessing Active Learning Adoption in Contemporary NLP: A Community Survey EACL 2026 ReAttn: Improving Attention-based Re-ranking via Attention Re-weighting EACL 2026 RECAP: Resistance Capture in Text-based Mental Health Counseling with Large Language Models CoNLL 2026 RECAP: REwriting Conversations for Intent Understanding in Agentic Planning EACL 2026 RecCocktail: A Generalizable and Efficient Framework for LLM-Based Recommendation AAAI 2026 ReciFine: Finely Annotated Recipe Dataset for Controllable Recipe Generation EACL 2026 RECIPE-TKG: From Sparse History to Structured Reasoning for LLM-based Temporal Knowledge Graph Completion EACL 2026 ReCode: Updating Code API Knowledge with Reinforcement Learning AAAI 2026 Reconstruction Attack-Resistant Inference Paradigm for LLM Cloud Services AAAI 2026 Recovering Coherent Affective Patterns: Addressing Modality Missing in Multimodal Sentiment Analysis AAAI 2026 Rectify Evaluation Preference: Improving LLMs’ Critique on Math Reasoning via Perplexity-aware Reinforcement Learning AAAI 2026 Redefining Retrieval Evaluation in the Era of LLMs EACL 2026 ReFACT: A Benchmark for Scientific Confabulation Detection with Positional Error Annotations EACL 2026 ReFEree: Reference-Free and Fine-Grained Method for Evaluating Factual Consistency in Real-World Code Summarization ACL 2026 Reference-Free Schema Generation for Literature Review Tables via Multi-Faceted Rewards ACL 2026 ReFINE: A Reward-Based Framework for Interpretable and Nuanced Evaluation of Radiology Report Generation AAAI 2026 ReFineVQA: Iterative Refinement of Video Description via Feedback Generation for Video Question Answering WACV 2026 Refining and Reusing Annotation Guidelines for LLM Annotation ACL 2026 Reflection in the Dark: Exposing and Escaping the Black Box in Reflective Prompt Optimization ACL 2026 ReflectiveRAG: Rethinking Adaptivity in Retrieval-Augmented Generation EACL 2026