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.
@article{arxiv.2602.03417,
title = {FactNet: A Billion-Scale Knowledge Graph for Multilingual Factual Grounding},
author = {Yingli Shen and Wen Lai and Jie Zhou and Xueren Zhang and Yudong Wang and Kangyang Luo and Shuo Wang and Ge Gao and Alexander Fraser and Maosong Sun},
journal= {arXiv preprint arXiv:2602.03417},
year = {2026}
}