reinforcement learning from human feedback

InferAligner: Inference-Time Alignment for Harmlessness through Cross-Model Guidance EMNLP 2024 InfoRM: Mitigating Reward Hacking in RLHF via Information-Theoretic Reward Modeling NeurIPS 2024 Interpretable Preferences via Multi-Objective Reward Modeling and Mixture-of-Experts EMNLP 2024 Interpreting Learned Feedback Patterns in Large Language Models NeurIPS 2024 Inverse-Q*: Token Level Reinforcement Learning for Aligning Large Language Models Without Preference Data EMNLP 2024 Learning Goal-Conditioned Representations for Language Reward Models NeurIPS 2024 Leftover Lunch: Advantage-based Offline Reinforcement Learning for Language Models ICLR 2024 Let Me Teach You: Pedagogical Foundations of Feedback for Language Models EMNLP 2024 LIRE: listwise reward enhancement for preference alignment ACL 2024 Making RL with Preference-based Feedback Efficient via Randomization ICLR 2024 MAPO: Advancing Multilingual Reasoning through Multilingual-Alignment-as-Preference Optimization ACL 2024 Margin Matching Preference Optimization: Enhanced Model Alignment with Granular Feedback EMNLP 2024 Mission Impossible: A Statistical Perspective on Jailbreaking LLMs NeurIPS 2024 Mitigating Reward Overoptimization via Lightweight Uncertainty Estimation NeurIPS 2024 Multimodal Large Language Models Make Text-to-Image Generative Models Align Better NeurIPS 2024 Navigating Noisy Feedback: Enhancing Reinforcement Learning with Error-Prone Language Models EMNLP 2024 NEFTune: Noisy Embeddings Improve Instruction Finetuning ICLR 2024 ODIN: Disentangled Reward Mitigates Hacking in RLHF ICML 2024 One-Shot Safety Alignment for Large Language Models via Optimal Dualization NeurIPS 2024 Online Iterative Reinforcement Learning from Human Feedback with General Preference Model NeurIPS 2024 On-Policy Distillation of Language Models: Learning from Self-Generated Mistakes ICLR 2024 On the Limited Generalization Capability of the Implicit Reward Model Induced by Direct Preference Optimization EMNLP 2024 Optimizing Language Models with Fair and Stable Reward Composition in Reinforcement Learning EMNLP 2024 PARL: A Unified Framework for Policy Alignment in Reinforcement Learning from Human Feedback ICLR 2024 Perplexity-aware Correction for Robust Alignment with Noisy Preferences NeurIPS 2024