Saved in:
Bibliographic Details
Main Authors: Lin, Tung-Wei, Fierro, Gabe, Li, Han, Hong, Tianzhen, Nuzzo, Pierluigi, Sangiovanni-Vinentelli, Alberto
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2507.22419
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911083634098176
author Lin, Tung-Wei
Fierro, Gabe
Li, Han
Hong, Tianzhen
Nuzzo, Pierluigi
Sangiovanni-Vinentelli, Alberto
author_facet Lin, Tung-Wei
Fierro, Gabe
Li, Han
Hong, Tianzhen
Nuzzo, Pierluigi
Sangiovanni-Vinentelli, Alberto
contents We present a systematic approach for evaluating the quality of knowledge graph repairs with respect to constraint violations defined in shapes constraint language (SHACL). Current evaluation methods rely on \emph{ad hoc} datasets, which limits the rigorous analysis of repair systems in more general settings. Our method addresses this gap by systematically generating violations using a novel mechanism, termed violation-inducing operations (VIOs). We use the proposed evaluation framework to assess a range of repair systems which we build using large language models. We analyze the performance of these systems across different prompting strategies. Results indicate that concise prompts containing both the relevant violated SHACL constraints and key contextual information from the knowledge graph yield the best performance.
format Preprint
id arxiv_https___arxiv_org_abs_2507_22419
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Systematic Evaluation of Knowledge Graph Repair with Large Language Models
Lin, Tung-Wei
Fierro, Gabe
Li, Han
Hong, Tianzhen
Nuzzo, Pierluigi
Sangiovanni-Vinentelli, Alberto
Databases
Artificial Intelligence
We present a systematic approach for evaluating the quality of knowledge graph repairs with respect to constraint violations defined in shapes constraint language (SHACL). Current evaluation methods rely on \emph{ad hoc} datasets, which limits the rigorous analysis of repair systems in more general settings. Our method addresses this gap by systematically generating violations using a novel mechanism, termed violation-inducing operations (VIOs). We use the proposed evaluation framework to assess a range of repair systems which we build using large language models. We analyze the performance of these systems across different prompting strategies. Results indicate that concise prompts containing both the relevant violated SHACL constraints and key contextual information from the knowledge graph yield the best performance.
title Systematic Evaluation of Knowledge Graph Repair with Large Language Models
topic Databases
Artificial Intelligence
url https://arxiv.org/abs/2507.22419