SourceScore

Verified claim · AI-ML · 100% confidence

Self-RAG introduced in: Asai et al. 2023 — self-reflective retrieval-augmented generation.

Last verified 2026-05-16 · Methodology veritas-v0.1 · c0219cf87124d20d

Structured fields

Subject
Self-RAG
Predicate
introduced_in
Object
Asai et al. 2023 — self-reflective retrieval-augmented generation
Confidence
100%
Tags
self-rag · rag · self-reflection · uw-nlp · allenai · 2023 · introduced_in

Sources (2)

  1. [1] preprint · arXiv (Asai, Wu, Wang, Sil, Hajishirzi / University of Washington + Allen Institute for AI) · 2023-10-17

    Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection
    We introduce a new framework called Self-Reflective Retrieval-Augmented Generation (Self-RAG) that enhances an LM's quality and factuality through retrieval and self-reflection. Our framework trains a single arbitrary LM that adaptively retrieves passages on-demand, and generates and reflects on retrieved passages and its own generations using special tokens, called reflection tokens.
  2. [2] official blog · Asai et al. / University of Washington · 2023-10-17

    Self-RAG — official project page

Cite this claim

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

Self-RAG introduced in: Asai et al. 2023 — self-reflective retrieval-augmented generation. — SourceScore Claim c0219cf87124d20d (verified 2026-05-16). https://sourcescore.org/api/v1/claims/c0219cf87124d20d.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/c0219cf87124d20d/" width="100%" height="360" frameborder="0" loading="lazy" title="Self-RAG introduced in: Asai et al. 2023 — self-reflective retrieval-augmented generation."></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/c0219cf87124d20d.json

JavaScript / TypeScript

const r = await fetch("https://sourcescore.org/api/v1/claims/c0219cf87124d20d.json"); const envelope = await r.json(); console.log(envelope.claim.statement); // "Self-RAG introduced in: Asai et al. 2023 — self-reflective retrieval-augmented generation."

Python

import httpx r = httpx.get("https://sourcescore.org/api/v1/claims/c0219cf87124d20d.json") envelope = r.json() print(envelope["claim"]["statement"]) # "Self-RAG introduced in: Asai et al. 2023 — self-reflective retrieval-augmented generation."

LangChain (retrieve-then-cite)

from langchain_core.tools import tool import httpx @tool def get_self_rag_fact() -> dict: """Fetch the verified SourceScore claim for Self-RAG.""" r = httpx.get("https://sourcescore.org/api/v1/claims/c0219cf87124d20d.json") return r.json()