# Zero-shot Fact Verification by Claim Generation

Source: [Zero-shot Fact Verification by Claim Generation](<https://www.sota2.com/research/paper/68fa6a0d1e209131cea25cd8>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-01-04T05:02:38.152Z

Authors: Liangming Pan, Wenhu Chen, Wenhan Xiong, Min-Yen Kan, William Yang Wang

Published: 2021-05-31T03:13:52.000Z

## Abstract

Neural models for automated fact verification have achieved promising results thanks to the availability of large, human-annotated datasets. However, for each new domain that requires fact verification, creating a dataset by manually writing claims and linking them to their supporting evidence is expensive. We develop QACG, a framework for training a robust fact verification model by using automatically generated claims that can be supported, refuted, or unverifiable from evidence from Wikipedia. QACG generates question-answer pairs from the evidence and then converts them into different types of claims. Experiments on the FEVER dataset show that our QACG framework significantly reduces the demand for human-annotated training data. In a zero-shot scenario, QACG improves a RoBERTa model's F1 from 50% to 77%, equivalent in performance to 2K+ manually-curated examples. Our QACG code is publicly available.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Fact Verification on FEVER S R](<https://www.sota2.com/research/sota/fact-verification-on-fever-s-r.md>): Fact Verification; FEVER S R; Precision: 78.1.

- [Fact Verification on FEVER-Symmetric](<https://www.sota2.com/research/sota/fact-verification-on-fever-symmetric.md>): Fact Verification; FEVER-Symmetric; Precision: 77.3.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2105.14682>)

[PDF](<https://arxiv.org/pdf/2105.14682.pdf>)

[Implementation](<https://github.com/teacherpeterpan/Zero-shot-Fact-Verification>)
