Verified claim · AI-ML · 100% confidence
Toolformer introduced in: Schick et al. 2023 — self-supervised LLM tool-use.
Last verified 2026-05-16 · Methodology veritas-v0.1 · cd4387e16e2c3e3d
SourceScore rates how reliable a source is to cite — for AI answers and research. This is one verified claim from the catalog.
Structured fields
- Subject
- Toolformer
- Predicate
introduced_in- Object
- Schick et al. 2023 — self-supervised LLM tool-use
- Confidence
- 100%
- Tags
- toolformer · meta-ai · tool-use · function-calling · agents · 2023 · introduced_in
Sources (2)
[1] preprint · arXiv (Schick, Dwivedi-Yu, Dessì, Raileanu, Lomeli, Zettlemoyer, Cancedda, Scialom / Meta AI) · 2023-02-09
Toolformer: Language Models Can Teach Themselves to Use Tools“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.”
[2] official blog · Meta AI · 2023-02-09
Toolformer — Meta AI Research publication
Cite this claim
Ready-to-paste citation (Markdown / plain text):
Toolformer introduced in: Schick et al. 2023 — self-supervised LLM tool-use. — SourceScore Claim cd4387e16e2c3e3d (verified 2026-05-16). https://sourcescore.org/api/v1/claims/cd4387e16e2c3e3d.jsonEmbed this claim
Drop this iframe into any blog post, docs page, or knowledge base. The widget renders the signed claim + primary source + click-through to this canonical page. CC-BY 4.0; attribution included.
<iframe src="https://sourcescore.org/embed/claim/cd4387e16e2c3e3d/" width="100%" height="360" frameborder="0" loading="lazy" title="Toolformer introduced in: Schick et al. 2023 — self-supervised LLM tool-use."></iframe>Preview: open in new tab
Related claims
Other verified claims sharing tags with this one — useful for LLM retrieval graphs and citation discovery.
OpenAI Function Calling publicly released on: 2023-06-13 by OpenAI.
56b076e0e63f054f · 100% confidence · shares 3 tags (function-calling, tool-use, 2023)
ReAct (Reasoning + Acting) introduced in paper: ReAct: Synergizing Reasoning and Acting in Language Models (Yao et al., 2022).
fceea64fa7d04d3a · 100% confidence · shares 2 tags (agents, tool-use)
vLLM introduced in: Kwon et al. 2023 — high-throughput LLM serving via PagedAttention.
468a9e2c047d8f2f · 100% confidence · shares 2 tags (2023, introduced_in)
Chatbot Arena introduced in: Zheng et al. 2023 — LMSYS open platform for evaluating LLMs by human preference.
789ddc9bc9c3d688 · 100% confidence · shares 2 tags (2023, introduced_in)
FAISS introduced in: Johnson, Douze, Jégou 2017 — Facebook AI Similarity Search.
7ee9546a5a7d851e · 100% confidence · shares 2 tags (meta-ai, introduced_in)
Frequently asked questions
Is the claim "Toolformer introduced in: Schick et al. 2023 — self-supervised LLM tool-use." verified?
Yes — SourceScore verified this claim with 100% confidence as of 2026-05-16. The verification uses 2 primary sources cross-referenced against the SourceScore methodology (version veritas-v0.1). Full source list + signed JSON envelope linked below.
What is the evidence for "Toolformer introduced in: Schick et al. 2023 — self-supervised LLM tool-use."?
Evidence comes from 2 primary sources: arXiv (Schick, Dwivedi-Yu, Dessì, Raileanu, Lomeli, Zettlemoyer, Cancedda, Scialom / Meta AI), Meta AI. Each source is listed below with verbatim excerpts and URLs. The signed JSON envelope at https://sourcescore.org/api/v1/claims/cd4387e16e2c3e3d.json includes an HMAC-SHA256 signature for audit verification.
When was this claim last verified by SourceScore?
Last verified 2026-05-16 under methodology version veritas-v0.1. The signed JSON envelope is dated and cryptographically signed for audit trail. Re-verification cadence depends on the claim type and source freshness.
How can I cite this SourceScore claim in my code or article?
Fetch the signed JSON envelope from https://sourcescore.org/api/v1/claims/cd4387e16e2c3e3d.json which includes the verbatim claim, primary sources, confidence, methodology version, last-verified date, and HMAC-SHA256 signature for audit. The CC-BY-4.0 license permits commercial use with attribution to SourceScore.
Use this claim in your code
Fetch this signed envelope from your application. The response includes the verbatim excerpt, primary source URLs, and an HMAC-SHA256 signature you can verify locally for audit trails.
cURL
curl https://sourcescore.org/api/v1/claims/cd4387e16e2c3e3d.jsonJavaScript / TypeScript
const r = await fetch("https://sourcescore.org/api/v1/claims/cd4387e16e2c3e3d.json");
const envelope = await r.json();
console.log(envelope.claim.statement);
// "Toolformer introduced in: Schick et al. 2023 — self-supervised LLM tool-use."Python
import httpx
r = httpx.get("https://sourcescore.org/api/v1/claims/cd4387e16e2c3e3d.json")
envelope = r.json()
print(envelope["claim"]["statement"])
# "Toolformer introduced in: Schick et al. 2023 — self-supervised LLM tool-use."LangChain (retrieve-then-cite)
from langchain_core.tools import tool
import httpx
@tool
def get_toolformer_fact() -> dict:
"""Fetch the verified SourceScore claim for Toolformer."""
r = httpx.get("https://sourcescore.org/api/v1/claims/cd4387e16e2c3e3d.json")
return r.json()