See also Interactive NLP Workshop - References and Awesome RLHF

• Wang et al 2021 - Putting Humans in the Natural Language Processing Loop: A Survey
• Blog posts
  • HuggingFace - Illustrating Reinforcement Learning from Human Feedback (RLHF)

• Ribeiro & Lundberg 2022 - Adaptive Testing and Debugging of NLP Models
• Interactive AI Model Debugging and Correction (2022 Thesis) (talk)
• InstructGPT: Ouyang et al 2022 - Training Language Models to Follow Instructions with Human Feedback
• Yu et al 2023 - Teaching Language Models to Self-Improve through Interactive Demonstrations
• VAL: Interactive Task Learning with GPT Dialog Parsing This is in an HCI conference

• Lertvittayakumjorn et al 2020 - FIND: Human-in-the-Loop Debugging Deep Text Classifiers

• Wang et al 2016 - Naturalizing a Programming Language via Interactive Learning
• Karamcheti et al 2020 - Learning Adaptive Language Interfaces through Decomposition
• Mo et al 2021 - Towards Transparent Interactive Semantic Parsing via Step-by-Step Correction

• Peris & Casacuberta 2018 - Active Learning for Interactive Neural Machine Translation of Data Streams

• Khashabi et al 2021 - GENIE: A Leaderboard for Human-in-the-Loop Evaluation of Text Generation

RLHF: Reinforcement Learning with Human Feedback. This definition is quite general, and would apply to any method of reinforcement learning with human feedback. Actually RLHF usually refers to a specific method of doing this. For a quick a overview, see section 3 of Rafailov 2023.

• Quick overview: section 3 of Rafailov 2023 or section of 1.1 of Chowdhury 2024
• Lil'Log 2018 - Policy Gradient Algorithms
• Kaufmann et al 2023 - A Survey of Reinforcement Learning from Human Feedback
• 2023 - Secrets of RLHF in Large Language Models Part I: PPO
• Wang et al 2024 - Secrets of RLHF in Large Language Models Part II: Reward Modeling
• Chaudhari et al 2024 - RLHF Deciphered: A Critical Analysis of Reinforcement Learning from Human Feedback for LLMs Really good explanation of PPO in section 6 (why each piece is necessary)
• Jiang et al 2024 - A Survey on Human Preference Learning for Large Language Models
• Lambert - Reinforcement Learning from Human Feedback Nathan's RLHF book. Very good website

• Christiano et al 2017 - Deep Reinforcement Learning from Human Preferences Introduced the setup of RLHF
• Ziegler et al 2019 - Fine-Tuning Language Models from Human Preferences Early RLHF paper, before it was called RLHF
• Stiennon et al 2020 - Learning to summarize from human feedback
• Askell et al 2021 - A General Language Assistant as a Laboratory for Alignment Introduced the acronym RLHF
• InstructGPT: Ouyang et al 2022 - Training language models to follow instructions with human feedback This is essentially inverse-reinforcement learning (such as this) applied to LMs. Background papers:
  • Used PPO: Schulman et al 2017 - Proximal Policy Optimization Algorithms
  • Ziegler 2019 - Fine-Tuning Language Models from Human Preferences
  • Stiennon et al 2020 - Learning to Summarize from Human Feedback
• Bai et al 2022 - Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback
• Rafailov et al 2023 - Direct Preference Optimization: Your Language Model is Secretly a Reward Model
• Wu et al 2023 - Fine-Grained Human Feedback Gives Better Rewards for Language Model Training
• Gao et al 2024 - Regressing the Relative Future: Efficient Policy Optimization for Multi-turn RLHF
• Wang et al 2025 - Text2Grad: Reinforcement Learning from Natural Language Feedback

• Surge AI

• InterNLP @ ACL 2021

• Percy Liang
• Sherry Tongshuang Wu (homepage)

• HCI and NLP
• Instruction-Tuning
• Lifelong Learning
• Reinforcement Learning
• Self-Play