Reinforcement Learning from Human Feedback

Distributional Preference Learning: Understanding and Accounting for Hidden Context in RLHF ICLR 2024 Don’t Forget Your Reward Values: Language Model Alignment via Value-based Calibration EMNLP 2024 Dynamic Rewarding with Prompt Optimization Enables Tuning-free Self-Alignment of Language Models EMNLP 2024 Easy-to-Hard Generalization: Scalable Alignment Beyond Human Supervision NeurIPS 2024 Evaluating Large Language Model Biases in Persona-Steered Generation ACL 2024 Evolutionary Contrastive Distillation for Language Model Alignment EMNLP 2024 Exploring Domain Robust Lightweight Reward Models based on Router Mechanism ACL 2024 FactAlign: Long-form Factuality Alignment of Large Language Models EMNLP 2024 Fast Best-of-N Decoding via Speculative Rejection NeurIPS 2024 Filtered Direct Preference Optimization EMNLP 2024 Global Reward to Local Rewards: Multimodal-Guided Decomposition for Improving Dialogue Agents EMNLP 2024 Group Robust Preference Optimization in Reward-free RLHF NeurIPS 2024 Hindsight PRIORs for Reward Learning from Human Preferences ICLR 2024 How Far Can In-Context Alignment Go? Exploring the State of In-Context Alignment EMNLP 2024 Improving Context-Aware Preference Modeling for Language Models NeurIPS 2024 Improving Discriminative Capability of Reward Models in RLHF Using Contrastive Learning EMNLP 2024 Interpretable Preferences via Multi-Objective Reward Modeling and Mixture-of-Experts EMNLP 2024 Interpreting Learned Feedback Patterns in Large Language Models NeurIPS 2024 LACIE: Listener-Aware Finetuning for Calibration in Large Language Models NeurIPS 2024 LeDex: Training LLMs to Better Self-Debug and Explain Code NeurIPS 2024 Leftover Lunch: Advantage-based Offline Reinforcement Learning for Language Models ICLR 2024 LIONs: An Empirically Optimized Approach to Align Language Models EMNLP 2024 LIRE: listwise reward enhancement for preference alignment ACL 2024 Making RL with Preference-based Feedback Efficient via Randomization ICLR 2024 Margin Matching Preference Optimization: Enhanced Model Alignment with Granular Feedback EMNLP 2024