Check long answers fact by fact
Split a long answer into atomic claims and verify each against search or a corpus.
Decompose the output into individual factual claims, retrieve evidence for each, and label each as supported or not. Use it as a post-hoc filter on outputs or as an evaluation metric during development.
Contexts: Retrieval-augmented QA, Chat assistant, LLM as judge
Does it work?
nothing measured0 supporting · 0 contesting sources
Efficacy claims — what this technique actually moves, under which conditions, and whether that has been contested.
1 more condition from claims reviewed by AI, listed with the claims below.
No efficacy claim filed yet. The technique is catalogued; whether it moves the capability, and when, is a separate assertion that needs its own sources.
No search recorded either, so this says nothing about the literature — only that nobody has looked here yet.
Code
- https://github.com/shmsw25/FActScore — FActScore decomposition and scoring.verified 2026-09-02
- https://github.com/google-deepmind/long-form-factuality — SAFE, search-augmented factuality evaluator.verified 2026-09-02
Sources
Whether a technique works is a claim. What you file here becomes a claim about this technique under the first capability it addresses, with your evidence as its source, and moves the standing above the same way a paper would.