{
  "apiVersion": "v1",
  "methodology": "https://sourcescore.org/methodology/",
  "canonical": "https://sourcescore.org/claims/cd4387e16e2c3e3d/",
  "claim": {
    "vertical": "ai-ml",
    "subject": "Toolformer",
    "predicate": "introduced_in",
    "object": "Schick et al. 2023 — self-supervised LLM tool-use",
    "confidence": 1,
    "sources": [
      {
        "url": "https://arxiv.org/abs/2302.04761",
        "title": "Toolformer: Language Models Can Teach Themselves to Use Tools",
        "publisher": "arXiv (Schick, Dwivedi-Yu, Dessì, Raileanu, Lomeli, Zettlemoyer, Cancedda, Scialom / Meta AI)",
        "publishedDate": "2023-02-09",
        "accessedDate": "2026-05-16",
        "type": "preprint",
        "excerpt": "In this paper, we show that LMs can teach themselves to use external tools via simple APIs and achieve the best of both worlds. We introduce Toolformer, a model trained to decide which APIs to call, when to call them, what arguments to pass, and how to best incorporate the results into future token prediction. This is done in a self-supervised way, requiring nothing more than a handful of demonstrations for each API."
      },
      {
        "url": "https://ai.meta.com/research/publications/toolformer-language-models-can-teach-themselves-to-use-tools/",
        "title": "Toolformer — Meta AI Research publication",
        "publisher": "Meta AI",
        "publishedDate": "2023-02-09",
        "accessedDate": "2026-05-16",
        "type": "official-blog"
      }
    ],
    "publishedAt": "2026-05-16T00:00:00Z",
    "lastVerified": "2026-05-16",
    "methodologyVersion": "veritas-v0.1",
    "tags": [
      "toolformer",
      "meta-ai",
      "tool-use",
      "function-calling",
      "agents",
      "2023",
      "introduced_in"
    ],
    "id": "cd4387e16e2c3e3d",
    "statement": "Toolformer introduced in: Schick et al. 2023 — self-supervised LLM tool-use."
  },
  "signature": {
    "algorithm": "HMAC-SHA256",
    "signedBy": "did:web:sourcescore.org",
    "signedAt": "2026-05-17T00:00:00.000Z",
    "signature": "9f7d1e2534764b8c2b231ee9d2947768f6f6d2a49ac6a0c2210a6365ad23ffc8"
  },
  "citedAs": "Toolformer introduced in: Schick et al. 2023 — self-supervised LLM tool-use. — SourceScore Claim cd4387e16e2c3e3d (verified 2026-05-16, signed 9f7d1e25…). https://sourcescore.org/claims/cd4387e16e2c3e3d/"
}