Reinforcement Learning from Human Feedback

Modeling User Preferences with Automatic Metrics: Creating a High-Quality Preference Dataset for Machine Translation EMNLP 2024 Navigating Noisy Feedback: Enhancing Reinforcement Learning with Error-Prone Language Models EMNLP 2024 Not All Preference Pairs Are Created Equal: A Recipe for Annotation-Efficient Iterative Preference Learning EMNLP 2024 Not Everything is All You Need: Toward Low-Redundant Optimization for Large Language Model Alignment EMNLP 2024 On Diversified Preferences of Large Language Model Alignment EMNLP 2024 One-Shot Safety Alignment for Large Language Models via Optimal Dualization NeurIPS 2024 On Softmax Direct Preference Optimization for Recommendation NeurIPS 2024 On the Limited Generalization Capability of the Implicit Reward Model Induced by Direct Preference Optimization EMNLP 2024 On the Relationship between Truth and Political Bias in Language Models EMNLP 2024 Optimizing Language Models for Human Preferences is a Causal Inference Problem UAI 2024 PARL: A Unified Framework for Policy Alignment in Reinforcement Learning from Human Feedback ICLR 2024 Pedagogical Alignment of Large Language Models EMNLP 2024 Personalized Steering of Large Language Models: Versatile Steering Vectors Through Bi-directional Preference Optimization NeurIPS 2024 Preference-Guided Reflective Sampling for Aligning Language Models EMNLP 2024 Privately Aligning Language Models with Reinforcement Learning ICLR 2024 Provable Offline Preference-Based Reinforcement Learning ICLR 2024 Provably Efficient Iterated CVaR Reinforcement Learning with Function Approximation and Human Feedback ICLR 2024 PURE: Aligning LLM via Pluggable Query Reformulation for Enhanced Helpfulness EMNLP 2024 Query-Policy Misalignment in Preference-Based Reinforcement Learning ICLR 2024 Reasons to Reject? Aligning Language Models with Judgments ACL 2024 Regularizing Hidden States Enables Learning Generalizable Reward Model for LLMs NeurIPS 2024 Rethinking the Role of Proxy Rewards in Language Model Alignment EMNLP 2024 Reward Modeling Requires Automatic Adjustment Based on Data Quality EMNLP 2024 RLHF Can Speak Many Languages: Unlocking Multilingual Preference Optimization for LLMs EMNLP 2024 Self-Supervised Alignment with Mutual Information: Learning to Follow Principles without Preference Labels NeurIPS 2024