# WiCE: Real-World Entailment for Claims in Wikipedia

Source: [WiCE: Real-World Entailment for Claims in Wikipedia](<https://www.sota2.com/research/paper/68fa70f21e209131cea4e423>)

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

Data updated: 2025-10-26T01:54:43.381Z

Authors: Ryo Kamoi, Tanya Goyal, Juan Diego Rodriguez, Greg Durrett

Published: 2023-03-02T17:45:32.000Z

## Abstract

Textual entailment models are increasingly applied in settings like fact-checking, presupposition verification in question answering, or summary evaluation. However, these represent a significant domain shift from existing entailment datasets, and models underperform as a result. We propose WiCE, a new fine-grained textual entailment dataset built on natural claim and evidence pairs extracted from Wikipedia. In addition to standard claim-level entailment, WiCE provides entailment judgments over sub-sentence units of the claim, and a minimal subset of evidence sentences that support each subclaim. To support this, we propose an automatic claim decomposition strategy using GPT-3.5 which we show is also effective at improving entailment models' performance on multiple datasets at test time. Finally, we show that real claims in our dataset involve challenging verification and retrieval problems that existing models fail to address.

## 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.

- [Claim Verification on PerplexityAI (test)](<https://www.sota2.com/research/sota/claim-verification-on-perplexityai-test.md>): Claim Verification; PerplexityAI (test); Verification Confidence: 76.3.

- [Claim Verification on ChatGPT (test)](<https://www.sota2.com/research/sota/claim-verification-on-chatgpt-test.md>): Claim Verification; ChatGPT (test); Verification Confidence: 43.1.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2303.01432>)

[PDF](<https://arxiv.org/pdf/2303.01432.pdf>)
