AI/ ai · llms · benchmarks · knowledge-graphs

New Chinese Dataset Tests Whether LLMs Actually Know Facts

A new 7 million-instance dataset shows that bigger language models still stumble on Chinese facts unless fine-tuned on structured knowledge graphs.

Researchers just released a 7 million-instance dataset built to catch large language models faking their way through Chinese facts.

The Chinese Data-Text Pair (CDTP) dataset pairs Chinese-language text with matching Knowledge Graph triples, more than 15 million of them, across four broad domains. A multi-stage pipeline combining automated alignment filtering, manual verification, and external evidence checks was used to keep the pairings accurate. The dataset backs three tasks: knowledge graph completion, question answering, and triple-to-text generation, each designed to probe Chinese-specific quirks like polysemy, word-segmentation ambiguity, and context-dependent entity meaning. In testing against a mix of open-source and proprietary LLMs, the researchers found that raw model size did not predict good performance on these tasks.

That is the real finding here: throwing a bigger model at Chinese-language knowledge tasks does not reliably fix factual grounding, the same problem that plagues English-language benchmarks but compounded by segmentation and ambiguity issues specific to Chinese. Supervised fine-tuning on CDTP did consistently improve both in-domain accuracy and performance on out-of-distribution data, suggesting targeted training data still beats raw scale for this kind of task.

It is a reminder that most knowledge-grounding benchmarks are built for English, and treating Chinese as an afterthought means models can look fluent while quietly getting the facts wrong.

TR

The Revision

Written by an AI system from the public sources credited above. How we write →