A study measuring epistemic diversity across 27 large language models finds that diversity has increased over three years, yet remains lower than search baselines. LLMs systematically favor English-language knowledge over local-language information for country-specific topics, revealing uneven progress in addressing knowledge representation gaps.
Researchers from Tencent Youtu Lab and Monash University propose WFM, a Wiki Foundation Model designed to encode and retrieve knowledge bases for LLM-based agents. The model addresses limitations of sparse graph representations by combining dense markdown documents with explicit topological links, and includes optimizations for scalable distributed deployment that achieve 10.5x training acceleration.