{
  "id": "2407.06023",
  "title": "Distilling System 2 into System 1",
  "authors": "Ping Yu, Jing Xu, Jason Weston, Ilia Kulikov",
  "first_public": "2024-07-08",
  "venue": "arXiv",
  "arxiv": "2407.06023",
  "paper_url": "https://arxiv.org/abs/2407.06023",
  "lens": [
    "internalized"
  ],
  "representation": [
    "hidden-state"
  ],
  "computation": [
    "depth-wise"
  ],
  "training": [
    "distillation"
  ],
  "questions": [
    "capability",
    "efficiency"
  ],
  "evidence": [
    "empirical"
  ],
  "modality": [
    "language"
  ],
  "summary": "Uses outputs from a slower deliberative process as training data for a faster model, studying when System-2-like behavior can be compressed into direct prediction.",
  "provenance": "Awesome-Latent-CoT",
  "author_names": [
    "Ping Yu",
    "Jing Xu",
    "Jason Weston",
    "Ilia Kulikov"
  ],
  "record_url": "https://latent-implicit-thinking.github.io/papers/2407.06023/",
  "legacy_record_url": "https://latent-implicit-thinking.github.io/papers/#paper-2407-06023",
  "citation_date": "2024-07-08",
  "json_url": "https://latent-implicit-thinking.github.io/papers/2407.06023/record.json",
  "markdown_url": "https://latent-implicit-thinking.github.io/papers/2407.06023/index.md",
  "bibtex_url": "https://latent-implicit-thinking.github.io/papers/2407.06023/citation.bib",
  "csl_url": "https://latent-implicit-thinking.github.io/papers/2407.06023/citation.csl.json"
}
