{"id":"url:rlhfbook.com","title":"Reinforcement Learning from Human Feedback","date":"2024-05-24","section":"Books","quality":null,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/20e354559fad09ad4d6338d104c9c3f822a48e7fbf86cd8afa1ddf951b223658/","source_url":"https://rlhfbook.com/","text_available":false,"authors":["Nathan Lambert"],"outgoing":[],"incoming":[{"source":"arxiv:2210.10760","target":"url:rlhfbook.com","evidence":"title","id":"arxiv:2210.10760","title":"Scaling Laws for Reward Model Overoptimization","url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/fd55acb4c34a2366d8f9c1fc0672a20be0ac4da8643118d0cbf627e891346d2d/"},{"source":"arxiv:2303.17651","target":"url:rlhfbook.com","evidence":"title","id":"arxiv:2303.17651","title":"Self-Refine: Iterative Refinement with Self-Feedback","url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/accef2157d87cf33be93cb3a9af246528b0a3742a9e2e700a194956fac8f5cf4/"},{"source":"arxiv:2304.05977","target":"url:rlhfbook.com","evidence":"title","id":"arxiv:2304.05977","title":"ImageReward: Learning and Evaluating Human Preferences for Text-to-Image Generation","url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/8244b779cf69cdaae850b1714a9f3d2f3388571e65bc93c56b03cb1f58c0f6dc/"},{"source":"arxiv:2402.13669","target":"url:rlhfbook.com","evidence":"title","id":"arxiv:2402.13669","title":"Self-Distillation Bridges Distribution Gap in Language Model Fine-Tuning","url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/1a8d11d48a58f35055e7f88f699cf42688a3698c63bd7026d5789f72a80581bf/"},{"source":"arxiv:2405.12250","target":"url:rlhfbook.com","evidence":"title","id":"arxiv:2405.12250","title":"Your Transformer is Secretly Linear","url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/6ae80c5f07c56011562d6b8323b0984ec0d36194708a43867aae691e2ddc5d86/"},{"source":"arxiv:2407.15017","target":"url:rlhfbook.com","evidence":"title","id":"arxiv:2407.15017","title":"Knowledge Mechanisms in Large Language Models: A Survey and Perspective","url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/8900dc2821aa61e59c5b1219cf9eb36dfaabf303c17d0064deaca653b5ec9a77/"},{"source":"arxiv:2407.21783","target":"url:rlhfbook.com","evidence":"title","id":"arxiv:2407.21783","title":"The Llama 3 Herd of Models","url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/de3cebb4c28bc5d41a843279f219dca14476284991ea5c7c0aeab7068a40e306/"},{"source":"arxiv:2412.14135","target":"url:rlhfbook.com","evidence":"title","id":"arxiv:2412.14135","title":"Scaling of Search and Learning: A Roadmap to Reproduce o1 from Reinforcement Learning Perspective","url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/5a0b4b0b524698ee5f30eab659b7cd5104f5fe6497c8dec2d0c4b9d332350047/"},{"source":"arxiv:2506.03106","target":"url:rlhfbook.com","evidence":"title","id":"arxiv:2506.03106","title":"Critique-GRPO: Advancing LLM Reasoning with Natural Language and Numerical Feedback","url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/b16b5772846ee30548a2d2c9cce1833ca3af6beb01c4a58f2dd5a69d809d55d4/"},{"source":"arxiv:2506.10139","target":"url:rlhfbook.com","evidence":"title","id":"arxiv:2506.10139","title":"Unsupervised Elicitation of Language Models","url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/f27ae3b426a87310071610dedea4c144b50b1be183434e32486b31562f9a3da9/"},{"source":"arxiv:2507.12856","target":"url:rlhfbook.com","evidence":"title","id":"arxiv:2507.12856","title":"Supervised Fine Tuning on Curated Data is Reinforcement Learning (and can be improved)","url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/5f6c1906eaa67369d9ff15b974756b89141d1b4cf9d7c0f6554e0d56f26e79be/"},{"source":"arxiv:2507.19457","target":"url:rlhfbook.com","evidence":"title","id":"arxiv:2507.19457","title":"GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning","url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/c1ef72d96fa3292590a6a3d112ab509840081b59aaa771cf42b8b0e8ef62ba08/"},{"source":"arxiv:2508.05629","target":"url:rlhfbook.com","evidence":"title","id":"arxiv:2508.05629","title":"On the Generalization of SFT: A Reinforcement Learning Perspective with Reward Rectification","url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/0a17fccfeffa8a04070bb16903a7217d8adee804cf42e0cfc8dd128d3390474f/"},{"source":"arxiv:2508.11408","target":"url:rlhfbook.com","evidence":"title","id":"arxiv:2508.11408","title":"On-Policy RL Meets Off-Policy Experts: Harmonizing Supervised Fine-Tuning and Reinforcement Learning via Dynamic Weighting","url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/48594da2e3f2cdfeb17195dd033d047235fc4b4ffb65030800f64c6faedc4fbe/"},{"source":"arxiv:2512.02807","target":"url:rlhfbook.com","evidence":"title","id":"arxiv:2512.02807","title":"SR-GRPO: Stable Rank as an Intrinsic Geometric Reward for Large Language Model Alignment","url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/ebb3b04baa11b5d0365ca4445da1c2f833108b680ea65272710ed66a57751c0e/"},{"source":"arxiv:2512.13961","target":"url:rlhfbook.com","evidence":"url","id":"arxiv:2512.13961","title":"Olmo 3","url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/8daa11a9729da9879a7e95c15d4eef3bab8579d2885a14102ed09db111221802/"},{"source":"arxiv:2601.05053","target":"url:rlhfbook.com","evidence":"title","id":"arxiv:2601.05053","title":"Reinforced Efficient Reasoning via Semantically Diverse Exploration","url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/74918d32c56962f9c5b2063026f5e2243a84e20c284eb3e37c882bd4681d1a11/"},{"source":"arxiv:2601.20802","target":"url:rlhfbook.com","evidence":"title","id":"arxiv:2601.20802","title":"Reinforcement Learning via Self-Distillation","url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/6073ec3d17b9a932a68e79ae078928f4635e40fc79cfcbc31709715d1f1e1ffa/"},{"source":"arxiv:2602.18037","target":"url:rlhfbook.com","evidence":"title","id":"arxiv:2602.18037","title":"Gradient Regularization Mitigates Reward Hacking in Reinforcement Learning from Human Feedback and Verifiable Rewards","url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/75161700a0f3e03055116a289c82e9f9fa7d8fee7a6f802e116216eac3a70e31/"},{"source":"arxiv:2604.08224","target":"url:rlhfbook.com","evidence":"title","id":"arxiv:2604.08224","title":"Externalization in LLM Agents: A Unified Review of Memory, Skills, Protocols and Harness Engineering","url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/392317a8b3bedec8258ff8288d69ac72bc9e60299c5f7bec8962838bb448c2ce/"},{"source":"arxiv:2604.20659","target":"url:rlhfbook.com","evidence":"title","id":"arxiv:2604.20659","title":"GRPO-VPS: Enhancing Group Relative Policy Optimization with Verifiable Process Supervision for Effective Reasoning","url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/42caf0f9c992f5df8bac4d0f7e45c3a5bf57879661f41febd01a047694d52628/"},{"source":"arxiv:2608.23875","target":"url:rlhfbook.com","evidence":"url","id":"arxiv:2608.23875","title":"AI Finds A Way","url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/afe34dd5ee58c2e9739f9651349c4c9180d95dabff51994a13339f48dfd0bb27/"},{"source":"url:openai.com/research/weak-to-strong-generalization","target":"url:rlhfbook.com","evidence":"title","id":"url:openai.com/research/weak-to-strong-generalization","title":"Weak-to-Strong Generalization: Eliciting Strong Capabilities With Weak Supervision","url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/fb7b23a617dce974dbb70db824c97c1de84afa11e1e290d5cb9f5bd88857e762/"}],"text_parts":[],"contents":[],"text_code_points":0,"source_markdown":null}