Large Language Models

RedOne: Revealing Domain-specific LLM Post-Training in Social Networking Services EMNLP 2025 Red Queen: Exposing Latent Multi-Turn Risks in Large Language Models ACL 2025 Red-Teaming for Uncovering Societal Bias in Large Language Models ACL 2025 RED: Unleashing Token-Level Rewards from Holistic Feedback via Reward Redistribution EMNLP 2025 Re-evaluating Open-ended Evaluation of Large Language Models ICLR 2025 Reference-Based Post-OCR Processing with LLM for Precise Diacritic Text in Historical Document Recognition AAAI 2025 ReFF: Reinforcing Format Faithfulness in Language Models Across Varied Tasks AAAI 2025 REFIND at SemEval-2025 Task 3: Retrieval-Augmented Factuality Hallucination Detection in Large Language Models SemEval 2025 Refining Salience-Aware Sparse Fine-Tuning Strategies for Language Models ACL 2025 ReflectEvo: Improving Meta Introspection of Small LLMs by Learning Self-Reflection ACL 2025 Ref-Long: Benchmarking the Long-context Referencing Capability of Long-context Language Models ACL 2025 Reframe Your Life Story: Interactive Narrative Therapist and Innovative Moment Assessment with Large Language Models EMNLP 2025 RefreshKV: Updating Small KV Cache During Long-form Generation ACL 2025 Refuse Whenever You Feel Unsafe: Improving Safety in LLMs via Decoupled Refusal Training ACL 2025 ReGraphRAG: Reorganizing Fragmented Knowledge Graphs for Multi-Perspective Retrieval-Augmented Generation EMNLP 2025 Regularized Best-of-N Sampling with Minimum Bayes Risk Objective for Language Model Alignment NAACL 2025 ReIFE: Re-evaluating Instruction-Following Evaluation NAACL 2025 Rejected Dialects: Biases Against African American Language in Reward Models NAACL 2025 Relation-Aware Prompting Makes Large Language Models Effective Zero-shot Relation Extractors EMNLP 2025 Relevant for the Right Reasons? Investigating Lexical Biases in Zero-Shot and Instruction-Tuned Rerankers EMNLP 2025 Relevant or Random: Can LLMs Truly Perform Analogical Reasoning? ACL 2025 Reliability of Distribution Predictions by LLMs: Insights from Counterintuitive Pseudo-Distributions NAACL 2025 Reliable and Diverse Evaluation of LLM Medical Knowledge Mastery ICLR 2025 Reliable and Efficient Amortized Model-based Evaluation ICML 2025 ReliableEval: A Recipe for Stochastic LLM Evaluation via Method of Moments EMNLP 2025