# Detecting Knowledge Inconsistencies Across Text, Tables, and Knowledge Graphs

DevFeed: [Detecting Knowledge Inconsistencies Across Text, Tables, and Knowledge Graphs](<https://devfeed.tech/articles/detecting-knowledge-inconsistencies-across-text-tables-and-knowledge-graphs-124461.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2607.25959>)

Author: Fanfu Wei, Thibault Ehrhart, Rapha\\"el Troncy

Published: 2026-11-09T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>)

Topics: [knowledge-engineering](<https://devfeed.tech/topics/knowledge-engineering.md>), [Wikidata](<https://devfeed.tech/topics/wikidata.md>), [llm-reasoning](<https://devfeed.tech/topics/llm-reasoning.md>)

Tags: [auditing](<https://devfeed.tech/tags/auditing.md>), [automatic](<https://devfeed.tech/tags/automatic.md>), [benchmark](<https://devfeed.tech/tags/benchmark.md>), [cross](<https://devfeed.tech/tags/cross.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-cl](<https://devfeed.tech/tags/cs-cl.md>), [datasets](<https://devfeed.tech/tags/datasets.md>), [detection](<https://devfeed.tech/tags/detection.md>), [errors](<https://devfeed.tech/tags/errors.md>), [explain](<https://devfeed.tech/tags/explain.md>), [framework](<https://devfeed.tech/tags/framework.md>), [graphs](<https://devfeed.tech/tags/graphs.md>), [knowledge](<https://devfeed.tech/tags/knowledge.md>), [knowledge-graphs](<https://devfeed.tech/tags/knowledge-graphs.md>), [llm](<https://devfeed.tech/tags/llm.md>), [llm-reasoning](<https://devfeed.tech/tags/llm-reasoning.md>), [modal](<https://devfeed.tech/tags/modal.md>), [noise](<https://devfeed.tech/tags/noise.md>), [practical](<https://devfeed.tech/tags/practical.md>), [qa](<https://devfeed.tech/tags/qa.md>), [tables](<https://devfeed.tech/tags/tables.md>), [text](<https://devfeed.tech/tags/text.md>)

## AI overview

Kontrast detects and categorizes inconsistencies between table-based answers and knowledge graph evidence using Text-to-SPARQL and LLM reasoning. The paper's taxonomy includes differences in information granularity, direct conflicts, temporal changes, and missing knowledge graph structure. Experiments on Table-QA datasets find such inconsistencies common and informative, but detection is limited by Text-to-SPARQL errors and noise. The authors describe systematic comparison as a way for text, tables, and knowledge graphs to complement and correct one another.

## Source excerpt

arXiv:2607.25959v3 Announce Type: replace-cross 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 https://github.com/ECLADATTA/KONTRAST.