{"id":"url:openai.com/research/weak-to-strong-generalization","title":"Weak-to-Strong Generalization: Eliciting Strong Capabilities With Weak Supervision","date":"2023-12-14","section":"AI safety and consciousness","quality":null,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/fb7b23a617dce974dbb70db824c97c1de84afa11e1e290d5cb9f5bd88857e762/","source_url":"https://openai.com/research/weak-to-strong-generalization","text_available":false,"authors":["Collin Burns","Pavel Izmailov","Jan Hendrik Kirchner","Bowen Baker"],"outgoing":[{"source":"url:openai.com/research/weak-to-strong-generalization","target":"url:rlhfbook.com","evidence":"title","id":"url:rlhfbook.com","title":"Reinforcement Learning from Human Feedback","url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/20e354559fad09ad4d6338d104c9c3f822a48e7fbf86cd8afa1ddf951b223658/"}],"incoming":[{"source":"arxiv:2402.03300","target":"url:openai.com/research/weak-to-strong-generalization","evidence":"id","id":"arxiv:2402.03300","title":"DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models","url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/636fb871904bc06f742cfdea069796f9e9665f95bd58dc63260eaff5154ef985/"},{"source":"arxiv:2406.11741","target":"url:openai.com/research/weak-to-strong-generalization","evidence":"id","id":"arxiv:2406.11741","title":"Transcendence: Generative Models Can Outperform The Experts That Train Them","url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/009cee51dbce762b177f0413e99ef4c30535501f77f54ed03aeb95de376319fd/"},{"source":"arxiv:2407.15017","target":"url:openai.com/research/weak-to-strong-generalization","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:2501.14082","target":"url:openai.com/research/weak-to-strong-generalization","evidence":"title","id":"arxiv:2501.14082","title":"Communicating Activations Between Language Model Agents","url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/e67d4addcda44093e242074332925d000726f87bd9538f6b318bdfc454a7dc13/"},{"source":"arxiv:2505.19590","target":"url:openai.com/research/weak-to-strong-generalization","evidence":"id","id":"arxiv:2505.19590","title":"Learning to Reason without External Rewards","url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/d8df33b706906a7abf4e660f54c75a81ffe2caaec8b0a10d1a6ad6ec63060832/"},{"source":"arxiv:2506.03106","target":"url:openai.com/research/weak-to-strong-generalization","evidence":"id","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:openai.com/research/weak-to-strong-generalization","evidence":"id","id":"arxiv:2506.10139","title":"Unsupervised Elicitation of Language Models","url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/f27ae3b426a87310071610dedea4c144b50b1be183434e32486b31562f9a3da9/"},{"source":"arxiv:2608.23875","target":"url:openai.com/research/weak-to-strong-generalization","evidence":"id","id":"arxiv:2608.23875","title":"AI Finds A Way","url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/afe34dd5ee58c2e9739f9651349c4c9180d95dabff51994a13339f48dfd0bb27/"},{"source":"url:ai-2027.com","target":"url:openai.com/research/weak-to-strong-generalization","evidence":"id","id":"url:ai-2027.com","title":"AI 2027 (Kokotajlo)","url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/3fd447e0ff58689ae00a4666e28bbd7faecd472dec7195ab1d524cb5402a1766/"}],"text_parts":[],"contents":[],"text_code_points":0,"source_markdown":null}