SEEK: 通过自适应分块进行多语言事实核查的语义证据提取
SEEK: Semantic Evidence Extraction via Adaptive ChunKing for Multilingual Fact-Checking
AI总结：
提出SEEK框架，通过自适应语义分块构建连贯证据块，并微调多语言大模型，在多语言事实核查中提升宏F1最高达20%。
摘要：
多语言事实核查需要既相关又足够完整的证据，以实现可靠的事实性预测。然而，现有系统通常依赖搜索片段、句子级证据或局部切分的段落，这可能会遗漏关键上下文并产生碎片化的证据。为克服这些限制，我们提出SEEK，一种自适应分块的语义证据提取框架，通过识别语义主题转换并保留局部验证上下文，从完整的事实核查文章中构建连贯的证据块。构建的块使用多语言编码器进行编码，然后使用LoRA适配器微调多语言大模型进行真实性预测。在X-FACT和RU22Fact上的实验表明，与语义分块相比，SEEK将宏F1提高了最多10%，与句子分块相比提高了19%，与搜索片段基线相比提高了20%。证据完整性和显著性分析进一步表明，SEEK保留了更丰富的验证上下文，并实现了更可靠的多语言事实核查。
英文摘要：
Multilingual fact verification requires evidence that is both relevant and sufficiently complete for reliable factuality prediction. However, existing systems often rely on search snippets, sentence-level evidence, or locally segmented passages, which can miss decisive context and produce fragmented evidence. To overcome these limitations, we propose SEEK, a Semantic Evidence Extraction with an adaptive chunKing framework that constructs coherent evidence chunks from full fact-checking articles by identifying semantic topic transitions and preserving local verification context. The constructed chunks are encoded using a multilingual encoder and then multilingual LLMs are finetuned using LoRA adapter for veracity prediction. Experiments on X-FACT and RU22Fact show that SEEK improves macro-f1 by up to 10% over semantic chunking, 19% over sentence chunking, and 20% over search-snippet baselines. Evidence completeness and significance analyses further show that SEEK preserves richer verification context and enables more reliable multilingual fact-checking.
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。
