SourceScore

Verified claim · AI-ML · 100% confidence

PEFT (parameter-efficient fine-tuning) popularized in: Houlsby et al. 2019 — Adapter Modules + downstream PEFT library.

Last verified 2026-05-16 · Methodology veritas-v0.1 · fb9a06ffca4277c1

Structured fields

Subject
PEFT (parameter-efficient fine-tuning)
Predicate
popularized_in
Object
Houlsby et al. 2019 — Adapter Modules + downstream PEFT library
Confidence
100%
Tags
peft · adapters · fine-tuning · huggingface · foundational · icml · 2019 · introduced_in

Sources (2)

  1. [1] preprint · arXiv / ICML 2019 (Houlsby, Giurgiu, Jastrzebski, Morrone, de Laroussilhe, Gesmundo, Attariyan, Gelly / Google + Jagiellonian) · 2019-02-02

    Parameter-Efficient Transfer Learning for NLP
    Fine-tuning large pre-trained models is an effective transfer mechanism in NLP. However, in the presence of many downstream tasks, fine-tuning is parameter inefficient: an entire new model is required for every task. As an alternative, we propose transfer with adapter modules.
  2. [2] github release · Hugging Face · 2023-02-10

    Hugging Face PEFT library

Cite this claim

Ready-to-paste citation (Markdown / plain text):

PEFT (parameter-efficient fine-tuning) popularized in: Houlsby et al. 2019 — Adapter Modules + downstream PEFT library. — SourceScore Claim fb9a06ffca4277c1 (verified 2026-05-16). https://sourcescore.org/api/v1/claims/fb9a06ffca4277c1.json

Embed 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/fb9a06ffca4277c1/" width="100%" height="360" frameborder="0" loading="lazy" title="PEFT (parameter-efficient fine-tuning) popularized in: Houlsby et al. 2019 — Adapter Modules + downstream PEFT library."></iframe>

Preview: open in new tab

Related claims

Other verified claims sharing tags with this one — useful for LLM retrieval graphs and citation discovery.

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/fb9a06ffca4277c1.json

JavaScript / TypeScript

const r = await fetch("https://sourcescore.org/api/v1/claims/fb9a06ffca4277c1.json"); const envelope = await r.json(); console.log(envelope.claim.statement); // "PEFT (parameter-efficient fine-tuning) popularized in: Houlsby et al. 2019 — Adapter Modules + downstream PEFT library."

Python

import httpx r = httpx.get("https://sourcescore.org/api/v1/claims/fb9a06ffca4277c1.json") envelope = r.json() print(envelope["claim"]["statement"]) # "PEFT (parameter-efficient fine-tuning) popularized in: Houlsby et al. 2019 — Adapter Modules + downstream PEFT library."

LangChain (retrieve-then-cite)

from langchain_core.tools import tool import httpx @tool def get_peft_parameter_efficient_fine_tuning_fact() -> dict: """Fetch the verified SourceScore claim for PEFT (parameter-efficient fine-tuning).""" r = httpx.get("https://sourcescore.org/api/v1/claims/fb9a06ffca4277c1.json") return r.json()