Direct Preference Optimization

{
  "author": null,
  "context": "Post-training alignment method during which undesirable behaviors emerged in the studied model.",
  "enrichment": {
    "is_stale": true
  },
  "norm_label": "Direct Preference Optimization",
  "source_url": null,
  "graphify_id": "dpo",
  "source_file": "xiao-aranguri-probe-data-attribution-2026.md",
  "imported_from": "/Users/antonborzov/Documents/Research.nosync/papers/extract_typed_out/xiao-aranguri-probe-data-attribution-2026/graph.json",
  "extracted_type": "framework",
  "graphify_file_type": "framework"
}