拆解事实核查能提效还是添乱？研究揭示其利弊权衡。
Decomposition Dilemmas: Does Claim Decomposition Boost or Burden Fact-Checking Performance?
- 通过错误分类分析拆解过程中的各类问题
- 发现拆解带来准确率提升但引入新噪声
- 为改进核查系统提供可操作的优化方向
事实核查流水线越来越多地采用「拆解-验证」范式，将文本分解为更小的陈述进行单独验证，再整合判断真假。尽管该方法广泛应用，其对最终核查性能的影响仍缺乏系统研究。部分研究显示拆解提升效果，另一些则观察到性能下降，表明其影响不一致。目前尚无全面分析揭示这种差异成因。本文通过误差案例分析与实验，提出拆解错误的分类体系，揭示了准确率提升与拆解引入噪声之间的权衡关系。研究为理解现有系统不稳定性提供了新视角，并为未来改进事实核查中的陈述拆解策略提供指导。
原文摘要 · Abstract (English)
Fact-checking pipelines increasingly adopt the Decompose-Then-Verify paradigm, where texts are broken down into smaller claims for individual verification and subsequently combined for a veracity decision. While decomposition is widely-adopted in such pipelines, its effects on final fact-checking performance remain underexplored. Some studies have reported improvements from decompostition, while others have observed performance declines, indicating its inconsistent impact. To date, no comprehensive analysis has been conducted to understand this variability. To address this gap, we present an in-depth analysis that explicitly examines the impact of decomposition on downstream verification performance. Through error case inspection and experiments, we introduce a categorization of decomposition errors and reveal a trade-off between accuracy gains and the noise introduced through decomposition. Our analysis provides new insights into understanding current system's instability and offers guidance for future studies toward improving claim decomposition in fact-checking pipelines.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。