FactNet：一个十亿级的知识图谱用于多语言事实 grounding
FactNet: A Billion-Scale Knowledge Graph for Multilingual Factual Grounding
AI总结：
FactNet通过结合17亿条维基数据语句和301亿条证据指针，构建了一个十亿级多语言知识图谱，提供事实 grounding 的评估框架，并验证了跨语言结构的知识迁移能力。
摘要：
大型语言模型容易产生事实性错误，并在非英语语言中难以将输出与可检索证据联系起来。现有资源面临取舍：结构化知识库缺乏文本 grounding，而 grounded 数据集则规模小且单语种。我们引入FactNet，一个十亿级开放资源，将17亿条维基数据语句与301亿条证据指针（来自316个原生维基百科版本）相结合。FactNet采用确定性构建流程，确保每个证据单元都能精确追溯到其来源。我们进一步建立了FactNet-Bench，一个用于知识图谱补全、问答和事实核查的评估套件，配备系统性的泄漏控制。实验表明，FactNet-Bench能够区分结构化、文本感知和LLM集成的方法，并且跨语言结构能够促进跨语言的知识迁移。
英文摘要：
Large language models hallucinate factual claims and struggle to ground their outputs in retrievable evidence, particularly in non-English languages. Existing resources impose a trade-off: structured knowledge bases lack textual grounding, whereas grounded datasets remain small and monolingual. We introduce FactNet, a billion-scale open resource that couples 1.7B Wikidata assertions with 3.01B evidence pointers drawn from 316 native Wikipedia editions. FactNet employs a deterministic construction pipeline, ensuring that every evidence unit is traceable to its source with byte-level precision. We further establish FactNet-Bench, an evaluation suite for Knowledge Graph Completion, Question Answering, and Fact Checking, equipped with systematic leakage controls. Experiments demonstrate that FactNet-Bench differentiates among structural, text-aware, and LLM-integrated methods, and that cross-lingual structure enables knowledge transfer across language tiers.
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。
