Reinforcement Learning from Human Feedback

Self-supervised Preference Optimization: Enhance Your Language Model with Preference Degree Awareness EMNLP 2024 Self-training Language Models for Arithmetic Reasoning EMNLP 2024 Social Reward: Evaluating and Enhancing Generative AI through Million-User Feedback from an Online Creative Community ICLR 2024 Teaching Language Models to Self-Improve by Learning from Language Feedback ACL 2024 The Accuracy Paradox in RLHF: When Better Reward Models Don’t Yield Better Language Models EMNLP 2024 The Language Barrier: Dissecting Safety Challenges of LLMs in Multilingual Contexts ACL 2024 The Trickle-down Impact of Reward Inconsistency on RLHF ICLR 2024 The Unlocking Spell on Base LLMs: Rethinking Alignment via In-Context Learning ICLR 2024 Towards Aligning Language Models with Textual Feedback EMNLP 2024 TS-Align: A Teacher-Student Collaborative Framework for Scalable Iterative Finetuning of Large Language Models EMNLP 2024 Unintended Impacts of LLM Alignment on Global Representation ACL 2024 Uni-RLHF: Universal Platform and Benchmark Suite for Reinforcement Learning with Diverse Human Feedback ICLR 2024 Unpacking DPO and PPO: Disentangling Best Practices for Learning from Preference Feedback NeurIPS 2024 VLFeedback: A Large-Scale AI Feedback Dataset for Large Vision-Language Models Alignment EMNLP 2024 When Your AIs Deceive You: Challenges of Partial Observability in Reinforcement Learning from Human Feedback NeurIPS 2024 WPO: Enhancing RLHF with Weighted Preference Optimization EMNLP 2024 AlpacaFarm: A Simulation Framework for Methods that Learn from Human Feedback NeurIPS 2023 A Study on Annotation Interfaces for Summary Comparison ACL 2023 BeaverTails: Towards Improved Safety Alignment of LLM via a Human-Preference Dataset NeurIPS 2023 Discovering Language Model Behaviors with Model-Written Evaluations ACL 2023 HuatuoGPT, Towards Taming Language Model to Be a Doctor EMNLP 2023 Human-in-the-loop Abstractive Dialogue Summarization ACL 2023 Improving Summarization with Human Edits EMNLP 2023 Just Ask for Calibration: Strategies for Eliciting Calibrated Confidence Scores from Language Models Fine-Tuned with Human Feedback EMNLP 2023 Learning New Skills after Deployment: Improving open-domain internet-driven dialogue with human feedback ACL 2023