用验证结果反哺文档排序，提升科学事实核查的证据检索效果。
+VeriRel: Verification Feedback to Enhance Document Retrieval for Scientific Fact Checking
- 将验证成功反馈融入文档排序机制，优化证据相关性评估。
- 在三个数据集上均显著优于现有方法，提升下游验证效果。
- 适合从事科学事实核查与信息检索交叉研究的读者。
科学事实核查的成功关键在于识别合适的支撑证据。然而，现有方法依赖通用信息检索算法，仅根据文档相关性排序，而非其对声明的支撑或反驳能力。本文提出 +VeriRel，将验证成功率纳入文档排序过程。在 SciFact、SciFact-Open 与 Check-Covid 三个科学事实核查数据集上的实验表明，+VeriRel 在文档证据检索任务中表现持续领先，并对下游验证任务产生积极影响。该研究揭示了将验证反馈融入文档相关性评估的潜力，为复杂文档中细粒度相关性判断提供了未来方向。
原文摘要 · Abstract (English)
Identification of appropriate supporting evidence is critical to the success of scientific fact checking. However, existing approaches rely on off-the-shelf Information Retrieval algorithms that rank documents based on relevance rather than the evidence they provide to support or refute the claim being checked. This paper proposes +VeriRel which includes verification success in the document ranking. Experimental results on three scientific fact checking datasets (SciFact, SciFact-Open and Check-Covid) demonstrate consistently leading performance by +VeriRel for document evidence retrieval and a positive impact on downstream verification. This study highlights the potential of integrating verification feedback to document relevance assessment for effective scientific fact checking systems. It shows promising future work to evaluate fine-grained relevance when examining complex documents for advanced scientific fact checking.
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。