Detecting Knowledge Inconsistencies Across Text, Tables, and Knowledge Graphs

• URL: http://arxiv.org/abs/2607.25959v2
• Date: Wed, 29 Jul 2026 10:29:17 GMT
• Title: Detecting Knowledge Inconsistencies Across Text, Tables, and Knowledge Graphs
• Abstract summary: This paper introduces a taxonomy of cross-modal knowledge inconsistencies, covering information granularity differences, direct conflicts, temporal changes, and KG incompleteness.<n>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.<n>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.
• Score: 0.6441446181237986
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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.

Related papers

• That's Deprecated! Understanding, Detecting, and Steering Knowledge Conflicts in Language Models for Code Generation [55.78914774437411]
  Large language models (LLMs) behave when faced with discrepancies between their parametric knowledge and conflicting information contained in a prompt.<n>We propose a domain-agnostic framework for constructing and interpreting such conflicts.<n>We show that activation-level steering can achieve up to a textbf12.6% improvement in steering success over a random baseline.
  arXiv  Detail & Related papers  (2025-10-21T22:27:56Z)
• Scalable and Explainable Enterprise Knowledge Discovery Using Graph-Centric Hybrid Retrieval [0.0]
  Modern enterprises manage vast knowledge distributed across heterogeneous systems such as Jira, Git repositories, Confluence, and wikis.<n>We present a modular hybrid retrieval framework that integrates Knowledge Base Language-Augmented Models (KBLam), DeepGraph representations, and embedding-driven semantic search.<n>The framework builds a unified knowledge graph from parsed repositories including code, pull requests, and commit histories.<n> Experiments on large-scale Git repositories show that the unified reasoning layer improves answer relevance by up to 80 percent compared with standalone GPT-based retrieval pipelines.
  arXiv  Detail & Related papers  (2025-10-13T02:56:36Z)
• A Benchmark for the Detection of Metalinguistic Disagreements between LLMs and Knowledge Graphs [0.0]
  We propose a benchmark for evaluating the detection of factual and metalinguistic disagreements between large language models (LLMs) and knowledge graph (KG)<n>An initial proof of concept of such a benchmark is available on Github.
  arXiv  Detail & Related papers  (2025-02-05T05:37:26Z)
• Harnessing Large Language Models for Knowledge Graph Question Answering via Adaptive Multi-Aspect Retrieval-Augmentation [81.18701211912779]
  We introduce an Adaptive Multi-Aspect Retrieval-augmented over KGs (Amar) framework.<n>This method retrieves knowledge including entities, relations, and subgraphs, and converts each piece of retrieved text into prompt embeddings.<n>Our method has achieved state-of-the-art performance on two common datasets.
  arXiv  Detail & Related papers  (2024-12-24T16:38:04Z)
• Disjointness Violations in Wikidata [0.0]
  We analyze the current modeling of disjointness on Wikidata. We use SPARQL queries to identify each culprit'' causing a disjointness violation and lay out formulas to identify and fix conflicting information.
  arXiv  Detail & Related papers  (2024-10-17T16:07:51Z)
• Integrating Large Language Models with Graph-based Reasoning for Conversational Question Answering [58.17090503446995]
  We focus on a conversational question answering task which combines the challenges of understanding questions in context and reasoning over evidence gathered from heterogeneous sources like text, knowledge graphs, tables, and infoboxes. Our method utilizes a graph structured representation to aggregate information about a question and its context.
  arXiv  Detail & Related papers  (2024-06-14T13:28:03Z)
• Studying Large Language Model Behaviors Under Context-Memory Conflicts With Real Documents [54.953320616069654]
  Retrieval-augmented generation mitigates many problems of fully parametric language models. In RAG, the model's knowledge can be updated from documents provided in context. We present a framework for studying such knowledge conflicts in a realistic setup.
  arXiv  Detail & Related papers  (2024-04-24T17:59:36Z)
• Robust and Scalable Model Editing for Large Language Models [75.95623066605259]
  We propose EREN (Edit models by REading Notes) to improve the scalability and robustness of LLM editing. Unlike existing techniques, it can integrate knowledge from multiple edits, and correctly respond to syntactically similar but semantically unrelated inputs.
  arXiv  Detail & Related papers  (2024-03-26T06:57:23Z)
• Text-To-KG Alignment: Comparing Current Methods on Classification Tasks [2.191505742658975]
  knowledge graphs (KG) provide dense and structured representations of factual information. Recent work has focused on creating pipeline models that retrieve information from KGs as additional context. It is not known how current methods compare to a scenario where the aligned subgraph is completely relevant to the query.
  arXiv  Detail & Related papers  (2023-06-05T13:45:45Z)
• Competency Problems: On Finding and Removing Artifacts in Language Data [50.09608320112584]
  We argue that for complex language understanding tasks, all simple feature correlations are spurious. We theoretically analyze the difficulty of creating data for competency problems when human bias is taken into account.
  arXiv  Detail & Related papers  (2021-04-17T21:34:10Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.