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

2025-08-22

AI Summary

This work addresses two key challenges in claim verification: (1) generative questions often embed unverified presuppositions, undermining reasoning consistency; and (2) large language models (LLMs) exhibit high prompt sensitivity, causing performance fluctuations of 3–6%. To mitigate these issues, we propose Presupposition-Free Decomposed Reasoning (PFDR), a novel framework that explicitly isolates and eliminates presuppositional content from questions, enforces structured multi-step verification, and decomposes tasks into prompt-invariant subproblems. Evaluated across standard benchmarks—FEVER, MultiFC, and SciFact—and major LLMs—including Llama-3, Qwen2, and GPT-4—PFDR achieves average accuracy gains of 2–5%. It substantially reduces variance induced by prompt perturbations, while enhancing transparency, robustness, and cross-model generalizability of the verification process.

Technology Category

• Natural Language Processing: Fact-Checking / Misinformation Detection (NLP Focus)
• Knowledge Representation and Reasoning: Common-Sense Reasoning
• Machine Learning: Large Multimodal Models (LMMs)

Application Category

• Search and Retrieval-Augmented AI: Large language models for search
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Economics, Online Markets and Human Computation: LLM based quality controls for crowd work

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.

Problem

• Addresses presupposition-induced inconsistencies in claim verification
• Mitigates prompt sensitivity in large language models
• Improves robustness through presupposition-free question decomposition

Innovation

• Presupposition-free question decomposition for verification
• Structured framework mitigating prompt sensitivity issues
• Robust claim verification across multiple LLMs