{"data":{"slug":"rlhf","etype":"concept","name":"RLHF","cat":"Training & Inference","subtitle":"Reinforcement learning from human feedback — the technique behind ChatGPT's manners.","summary":"RLHF trains a reward model from human preference comparisons, then optimizes the language model against it. Introduced at scale by InstructGPT (2022), it is why assistants follow instructions and refuse harm — and its quirks (sycophancy, reward hacking) drive research into alternatives like constitutional AI and direct preference optimization.","attrs":null,"kf":null,"aliases":["reinforcement learning from human feedback","DPO"],"ticker":null,"exchange":null,"hq":null,"founded":null,"website":null,"status":null,"region":null,"asof":"2026-01-15","sources":[{"url":"https://arxiv.org/abs/2203.02155","label":"InstructGPT paper"}]},"meta":{"found":true,"count":1,"served_from":"site cache (no live upstream calls)","as_of":"2026-10-14T09:50:09+00:00","disclaimer":"Research and information only — not investment advice. Structured records carry basis labels (vendor spec / reported / estimate); market quotes are delayed/indicative.","attribution":"Records compiled from vendor documentation, official filings and reputable public reporting; market quotes via financial data providers. See /data-sources."}}