Kontrast：检测文本、表格与知识图谱间的跨模态知识不一致

View PDF HTML (experimental)

Abstract:Wikipedia and Wikidata are widely used for information access, LLM pre-training, and retrieval-augmented generation. Their knowledge is deeply connected but scattered across text, tables, and knowledge graphs. This raises a practical question: when these modalities disagree, how can we detect and explain the conflict? We study this problem as modality-level inconsistency detection. We first introduce a taxonomy of cross-modal knowledge inconsistencies, covering information granularity differences, direct conflicts, temporal changes, and KG incompleteness. We then present Kontrast, an automatic framework that uses Text-to-SPARQL and LLM reasoning to compare table-based answers with KG evidence and categorize the resulting inconsistencies. Experiments on various Table-QA datasets show that cross-modal inconsistencies are common and informative. They reveal not only true knowledge conflicts, but also missing KG structure and temporal mismatches while being limited by Text-to-SPARQL errors and noise. Our analysis shows that text, tables, and KGs can complement and correct one another through systematic comparison. Kontrast provides a practical tool for large-scale knowledge auditing and establishes a benchmark for future work on cross-modal knowledge consistency. Code and data are available at this https URL.

Subjects:	Computation and Language (cs.CL); Artificial Intelligence (cs.AI)
Cite as:	arXiv:2607.25959 [cs.CL]
	(or arXiv:2607.25959v3 [cs.CL] for this version)
	https://doi.org/10.48550/arXiv.2607.25959 arXiv-issued DOI via DataCite

Submission history

From: Fanfu Wei [view email]
[v1] Tue, 28 Jul 2026 16:43:56 UTC (315 KB)
[v2] Wed, 29 Jul 2026 10:29:17 UTC (315 KB)
[v3] Fri, 6 Nov 2026 14:11:20 UTC (422 KB)