If We May De-Presuppose: Robustly Verifying Claims through Presupposition-Free Question Decomposition

TL;DR

This paper introduces a claim verification method that decomposes questions without presuppositions to improve robustness against prompt sensitivity and reduce inconsistencies in large language models.

Contribution

It proposes a novel presupposition-free question decomposition framework that enhances claim verification robustness across different prompts and models.

Findings

Reduces prompt sensitivity effects by 2-5%

Maintains consistent verification performance across datasets

Outperforms baseline methods in robustness tests

Abstract

Prior work has shown that presupposition in generated questions can introduce unverified assumptions, leading to inconsistencies in claim verification. Additionally, prompt sensitivity remains a significant challenge for large language models (LLMs), resulting in performance variance as high as 3-6%. While recent advancements have reduced this gap, our study demonstrates that prompt sensitivity remains a persistent issue. To address this, we propose a structured and robust claim verification framework that reasons through presupposition-free, decomposed questions. Extensive experiments across multiple prompts, datasets, and LLMs reveal that even state-of-the-art models remain susceptible to prompt variance and presupposition. Our method consistently mitigates these issues, achieving up to a 2-5% improvement.