FactNet: A Billion-Scale Knowledge Graph for Multilingual Factual Grounding

2026-02-03

AI Summary

This work addresses the challenge of factual hallucinations in large language models, which often lack traceable sources, by introducing FactNet—a large-scale multilingual knowledge graph constructed from Wikipedia across 316 languages. FactNet comprises 1.7 billion atomic facts and 3.01 billion byte-level reproducible evidence pointers, enabling precise attribution. Through a deterministic extraction and alignment pipeline, FactNet uniquely unifies structured knowledge with multilingual textual evidence, significantly enhancing auditability and coverage—including for low-resource languages. Evaluated on the FactNet-Bench benchmark, it achieves a fact grounding accuracy of 92.1%, demonstrating strong performance in knowledge graph completion, question answering, and fact verification tasks.

Technology Category

• Natural Language Processing: Fact-Checking / Misinformation Detection (NLP Focus)
• Knowledge Representation and Reasoning: Knowledge Representation Languages
• Data Mining & Knowledge Management: Linked Open Data, Knowledge Graphs & KB Completion

Application Category

• Semantics and Knowledge: Scalable techniques for the creation, curation, publication, maintenance, and consumption of large, Web-based, structured, reusable, knowledge graphs and ontologies
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Search and Retrieval-Augmented AI: Multilingual and cross-lingual Web search

Abstract

While LLMs exhibit remarkable fluency, their utility is often compromised by factual hallucinations and a lack of traceable provenance. Existing resources for grounding mitigate this but typically enforce a dichotomy: they offer either structured knowledge without textual context (e.g., knowledge bases) or grounded text with limited scale and linguistic coverage. To bridge this gap, we introduce FactNet, a massive, open-source resource designed to unify 1.7 billion atomic assertions with 3.01 billion auditable evidence pointers derived exclusively from 316 Wikipedia editions. Unlike recent synthetic approaches, FactNet employs a strictly deterministic construction pipeline, ensuring that every evidence unit is recoverable with byte-level precision. Extensive auditing confirms a high grounding precision of 92.1%, even in long-tail languages. Furthermore, we establish FactNet-Bench, a comprehensive evaluation suite for Knowledge Graph Completion, Question Answering, and Fact Checking. FactNet provides the community with a foundational, reproducible resource for training and evaluating trustworthy, verifiable multilingual systems.

Problem

• factual hallucinations
• knowledge grounding
• multilingual coverage
• traceable provenance
• structured knowledge

Innovation

• FactNet
• multilingual factual grounding
• deterministic knowledge graph construction
• auditable evidence
• Wikipedia-based knowledge base