Large Language Models

REVIVING YOUR MNEME: Predicting The Side Effects of LLM Unlearning and Fine-Tuning via Sparse Model Diffing EMNLP 2025 Revolve: Optimizing AI Systems by Tracking Response Evolution in Textual Optimization ICML 2025 Reward-Augmented Data Enhances Direct Preference Alignment of LLMs ICML 2025 Reward-Guided Prompt Evolving in Reinforcement Learning for LLMs ICML 2025 Reward-Guided Speculative Decoding for Efficient LLM Reasoning ICML 2025 Reward Translation via Reward Machine in Semi-Alignable MDPs ICML 2025 ReWiND: Language-Guided Rewards Teach Robot Policies without New Demonstrations CoRL 2025 Rewrite to Jailbreak: Discover Learnable and Transferable Implicit Harmfulness Instruction ACL 2025 ‘Rich Dad, Poor Lad’: How do Large Language Models Contextualize Socioeconomic Factors in College Admission ? EMNLP 2025 Richer Output for Richer Countries: Uncovering Geographical Disparities in Generated Stories and Travel Recommendations NAACL 2025 Right Now, Wrong Then: Non-Stationary Direct Preference Optimization under Preference Drift ICML 2025 RiOT: Efficient Prompt Refinement with Residual Optimization Tree ACL 2025 R.I.P.: Better Models by Survival of the Fittest Prompts ICML 2025 RIRAG: A Bi-Directional Retrieval-Enhanced Framework for Financial Legal QA in ObliQA Shared Task COLING 2025 RL, but don’t do anything I wouldn’t do UAI 2025 RLEF: Grounding Code LLMs in Execution Feedback with Reinforcement Learning ICML 2025 RLHF Algorithms Ranked: An Extensive Evaluation Across Diverse Tasks, Rewards, and Hyperparameters EMNLP 2025 RLMEval: Evaluating Research-Level Neural Theorem Proving EMNLP 2025 R-LoRA: Randomized Multi-Head LoRA for Efficient Multi-task Learning EMNLP 2025 RLTHF: Targeted Human Feedback for LLM Alignment ICML 2025 RMoA: Optimizing Mixture-of-Agents through Diversity Maximization and Residual Compensation ACL 2025 RMTBench: Benchmarking LLMs Through Multi-Turn User-Centric Role-Playing EMNLP 2025 RoboChemist: Long-Horizon and Safety-Compliant Robotic Chemical Experimentation CoRL 2025 RoboMonkey: Scaling Test-Time Sampling and Verification for Vision-Language-Action Models CoRL 2025 ROBOTO2: An Interactive System and Dataset for LLM-assisted Clinical Trial Risk of Bias Assessment EMNLP 2025