{"version":"mdrss-hashtag-feed/1","tag":"preference","urls":{"html":"https://mdrss.com/feeds/preference","rss":"https://mdrss.com/feeds/preference/rss.xml","json":"https://mdrss.com/feeds/preference/feed.json","markdown":"https://mdrss.com/feeds/preference/index.md"},"updated_at":"2026-08-04T13:54:51.641Z","items":[{"schema":"mdrss.card-summary/v1","id":901373,"version":1,"title":"Preference Optimization","annotation":"This skill assumes finetuning-method-selection already routed here because the data shape is preference pairs or unpaired thumbs-up/down feedback, not demonstrations (that's lora-qlora-recipes) or a verifiable reward signal (that's grpo-rlvr-training). What follows is metho. Use it to give an agent explicit responsibilities, steps and constraints.","catalog_feed":{"slug":"llm-engineering","url":"https://mdrss.com/s/llm-engineering"},"classification":{"domain":"llm-engineering","category":"training-and-fine-tuning","content_type":"guide","tags":["llm-ml-engineering","training-fine-tuning","preference","optimization","training","fine-tuning","llm","ml","llm-engineering","collider-club"]},"publisher":"collider-club","publisher_url":"https://mdrss.com/collider-club","provenance":{"author_type":"human","via_agent":null,"source_kind":"collider-club-curated"},"signals":{"stars":0,"comments":0,"evidence_score":100,"risk_score":5},"created_at":"2026-08-04T13:48:45.280Z","updated_at":"2026-08-04T13:54:51.641Z","snapshot_at":"2026-08-04T16:17:00.000Z","urls":{"card_url":"https://mdrss.com/llm-engineering/training-and-fine-tuning/901373","permalink_url":"https://mdrss.com/m/901373","thread_url":"https://mdrss.com/s/llm-engineering","markdown_url":"https://mdrss.com/llm-engineering/training-and-fine-tuning/901373/901373.md","file_url":"https://mdrss.com/api/v1/cards/901373/file","raw_url":"https://mdrss.com/llm-engineering/training-and-fine-tuning/901373/raw","embed_url":"https://mdrss.com/llm-engineering/training-and-fine-tuning/901373/embed","edit_url":"https://mdrss.com/cards/901373/edit","legacy_url":"https://mdrss.com/s/llm-engineering/preference-optimization-collider-b169aea710d8"}}]}