{
  "id": "2407.11004",
  "title": "The ALCHEmist: Automated Labeling 500x CHEaper Than LLM Data Annotators",
  "authors": "Tzu-Heng Huang, Catherine Cao, Vaishnavi Bhargava, Frederic Sala",
  "first_public": "2024-06-25",
  "first_public_source": "https://arxiv.org/abs/2407.11004",
  "arxiv_first_submission": "2024-06-25",
  "date_label": "arXiv v1",
  "arxiv": "2407.11004",
  "paper_url": "https://arxiv.org/abs/2407.11004",
  "venue": "NeurIPS 2024",
  "lens": [
    "neural-programs"
  ],
  "related_terms": [
    "ALCHEmist",
    "program synthesis",
    "automated labeling",
    "reusable tools"
  ],
  "summary": "Asks a language model to write labeling programs that can be saved and run locally.",
  "contribution": "Reuses generated code across many labeling decisions and combines noisy program outputs with weak supervision.",
  "limitations": "Label quality depends on the model’s ability to write useful programs. Complex tasks can produce code that is harder to inspect.",
  "program_form": "Symbolic labeling programs.",
  "conditioning": "A task description, labeling instructions, and a function signature.",
  "execution": "Generated programs label examples locally; their outputs can be combined to train a downstream model.",
  "relationship": "PAW evaluates an ALCHEmist-style approach. Both build reusable tools: ALCHEmist produces symbolic code, while PAW produces programs for a neural interpreter.",
  "relationship_source": "https://arxiv.org/html/2607.02512v1#S10",
  "provenance": "arXiv record and paper.",
  "author_names": [
    "Tzu-Heng Huang",
    "Catherine Cao",
    "Vaishnavi Bhargava",
    "Frederic Sala"
  ],
  "record_url": "https://programasweights.com/reading-list/papers/2407.11004/",
  "legacy_record_url": "https://programasweights.com/reading-list/papers/#paper-2407-11004",
  "citation_date": "2024-06-25",
  "json_url": "https://programasweights.com/reading-list/papers/2407.11004/record.json",
  "markdown_url": "https://programasweights.com/reading-list/papers/2407.11004/index.md",
  "bibtex_url": "https://programasweights.com/reading-list/papers/2407.11004/citation.bib",
  "csl_url": "https://programasweights.com/reading-list/papers/2407.11004/citation.csl.json",
  "publication": {
    "title": "The ALCHEmist: Automated Labeling 500x CHEaper than LLM Data Annotators",
    "author_names": [
      "Tzu-Heng Huang",
      "Catherine Cao",
      "Vaishnavi Bhargava",
      "Frederic Sala"
    ],
    "year": 2024,
    "type": "paper-conference",
    "container_title": "Advances in Neural Information Processing Systems",
    "url": "https://proceedings.neurips.cc/paper_files/paper/2024/hash/72802bef5cf1a3449e909b20c2ae18d5-Abstract-Conference.html",
    "source_url": "https://proceedings.neurips.cc/paper_files/paper/2024/hash/72802bef5cf1a3449e909b20c2ae18d5-Abstract-Conference.html",
    "verified_at": "2026-10-19",
    "volume": "37",
    "doi": "10.52202/079017-2003",
    "pages": "62648-62672"
  },
  "publication_bibtex_url": "https://programasweights.com/reading-list/papers/2407.11004/publication.bib",
  "publication_csl_url": "https://programasweights.com/reading-list/papers/2407.11004/publication.csl.json",
  "method_comparisons": [
    {
      "title": "Code and neural programs",
      "text": "ALCHEmist generates symbolic labeling programs. PAW compiles fuzzy functions into text and learned parameters. Both build an artifact once and reuse it; one runs as code, the other on a neural interpreter.",
      "source_ids": [
        "2407.11004",
        "2607.02512"
      ],
      "source_urls": [
        "https://proceedings.neurips.cc/paper_files/paper/2024/hash/72802bef5cf1a3449e909b20c2ae18d5-Abstract-Conference.html",
        "https://arxiv.org/html/2607.02512v1#S6"
      ],
      "source_labels": [
        "ALCHEmist paper",
        "PAW evaluation"
      ],
      "topic_id": "neural-programs",
      "topic_label": "Programs and reusable artifacts",
      "topic_url": "https://programasweights.com/reading-list/guides/fuzzy-functions/"
    }
  ]
}