检索-细化-校准：复杂断言事实核查的框架
Retrieve-Refine-Calibrate: A Framework for Complex Claim Fact-Checking
AI总结：
本文提出RRC框架，通过检索、细化和校准提升复杂断言事实核查的准确性。
摘要：
事实核查旨在基于检索到的证据验证断言的真实性。现有方法通常遵循分解范式，即将断言分解为子断言进行单独验证。然而，分解范式可能由于无关实体或证据引入噪声，最终降低验证准确性。为了解决这个问题，我们提出了一种基于大语言模型（LLMs）的检索-细化-校准（RRC）框架。具体而言，该框架首先识别断言中提到的实体并检索相关证据。然后，根据断言细化检索到的证据以减少无关信息。最后，通过重新评估低置信度预测来校准验证过程。在两个流行的事实核查数据集（HOVER和FEVEROUS-S）上的实验表明，我们的框架相比竞争基线实现了更优的性能。
英文摘要：
Fact-checking aims to verify the truthfulness of a claim based on the retrieved evidence. Existing methods typically follow a decomposition paradigm, in which a claim is broken down into sub-claims that are individually verified. However, the decomposition paradigm may introduce noise to the verification process due to irrelevant entities or evidence, ultimately degrading verification accuracy. To address this problem, we propose a Retrieve-Refine-Calibrate (RRC) framework based on large language models (LLMs). Specifically, the framework first identifies the entities mentioned in the claim and retrieves evidence relevant to them. Then, it refines the retrieved evidence based on the claim to reduce irrelevant information. Finally, it calibrates the verification process by re-evaluating low-confidence predictions. Experiments on two popular fact-checking datasets (HOVER and FEVEROUS-S) demonstrate that our framework achieves superior performance compared with competitive baselines.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
