Reinforcement Learning from Human Feedback

A Grounded Preference Model for LLM Alignment ACL 2024 Aligner: Efficient Alignment by Learning to Correct NeurIPS 2024 Aligners: Decoupling LLMs and Alignment EMNLP 2024 A SMART Mnemonic Sounds like “Glue Tonic”: Mixing LLMs with Student Feedback to Make Mnemonic Learning Stick EMNLP 2024 Automated Multi-level Preference for MLLMs NeurIPS 2024 BiasDPO: Mitigating Bias in Language Models through Direct Preference Optimization ACL 2024 Calibrated Self-Rewarding Vision Language Models NeurIPS 2024 ChatGLM-Math: Improving Math Problem-Solving in Large Language Models with a Self-Critique Pipeline EMNLP 2024 Contrastive Policy Gradient: Aligning LLMs on sequence-level scores in a supervised-friendly fashion EMNLP 2024 DACO: Towards Application-Driven and Comprehensive Data Analysis via Code Generation NeurIPS 2024 Decoding-Time Language Model Alignment with Multiple Objectives NeurIPS 2024 Discovering Preference Optimization Algorithms with and for Large Language Models NeurIPS 2024 DMoERM: Recipes of Mixture-of-Experts for Effective Reward Modeling ACL 2024 DogeRM: Equipping Reward Models with Domain Knowledge through Model Merging EMNLP 2024 Enhancing Alignment using Curriculum Learning & Ranked Preferences EMNLP 2024 Enhancing Language Model Alignment: A Confidence-Based Approach to Label Smoothing EMNLP 2024 Foundational Autoraters: Taming Large Language Models for Better Automatic Evaluation EMNLP 2024 GDPO: Learning to Directly Align Language Models with Diversity Using GFlowNets EMNLP 2024 Geometric-Averaged Preference Optimization for Soft Preference Labels NeurIPS 2024 Hybrid Alignment Training for Large Language Models ACL 2024 Inverse-Q*: Token Level Reinforcement Learning for Aligning Large Language Models Without Preference Data EMNLP 2024 Multi-modal Preference Alignment Remedies Degradation of Visual Instruction Tuning on Language Models ACL 2024 ORPO: Monolithic Preference Optimization without Reference Model EMNLP 2024 Perplexity-aware Correction for Robust Alignment with Noisy Preferences NeurIPS 2024 Preference Alignment with Flow Matching NeurIPS 2024