AmbiGraph-Eval: Can LLMs Effectively Handle Ambiguous Graph Queries?

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Tian, Yuchen, Li, Kaixin, Chen, Hao, Luo, Ziyang, Lin, Hongzhan, Schelter, Sebastian, Du, Lun, Ma, Jing
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866912535976869888
author Tian, Yuchen
Li, Kaixin
Chen, Hao
Luo, Ziyang
Lin, Hongzhan
Schelter, Sebastian
Du, Lun
Ma, Jing
author_facet Tian, Yuchen
Li, Kaixin
Chen, Hao
Luo, Ziyang
Lin, Hongzhan
Schelter, Sebastian
Du, Lun
Ma, Jing
contents Large Language Models (LLMs) have recently demonstrated strong capabilities in translating natural language into database queries, especially when dealing with complex graph-structured data. However, real-world queries often contain inherent ambiguities, and the interconnected nature of graph structures can amplify these challenges, leading to unintended or incorrect query results. To systematically evaluate LLMs on this front, we propose a taxonomy of graph-query ambiguities, comprising three primary types: Attribute Ambiguity, Relationship Ambiguity, and Attribute-Relationship Ambiguity, each subdivided into Same-Entity and Cross-Entity scenarios. We introduce AmbiGraph-Eval, a novel benchmark of real-world ambiguous queries paired with expert-verified graph query answers. Evaluating 9 representative LLMs shows that even top models struggle with ambiguous graph queries. Our findings reveal a critical gap in ambiguity handling and motivate future work on specialized resolution techniques.
format Preprint
id arxiv_https___arxiv_org_abs_2508_09631
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle AmbiGraph-Eval: Can LLMs Effectively Handle Ambiguous Graph Queries?
Tian, Yuchen
Li, Kaixin
Chen, Hao
Luo, Ziyang
Lin, Hongzhan
Schelter, Sebastian
Du, Lun
Ma, Jing
Databases
Artificial Intelligence
Large Language Models (LLMs) have recently demonstrated strong capabilities in translating natural language into database queries, especially when dealing with complex graph-structured data. However, real-world queries often contain inherent ambiguities, and the interconnected nature of graph structures can amplify these challenges, leading to unintended or incorrect query results. To systematically evaluate LLMs on this front, we propose a taxonomy of graph-query ambiguities, comprising three primary types: Attribute Ambiguity, Relationship Ambiguity, and Attribute-Relationship Ambiguity, each subdivided into Same-Entity and Cross-Entity scenarios. We introduce AmbiGraph-Eval, a novel benchmark of real-world ambiguous queries paired with expert-verified graph query answers. Evaluating 9 representative LLMs shows that even top models struggle with ambiguous graph queries. Our findings reveal a critical gap in ambiguity handling and motivate future work on specialized resolution techniques.
title AmbiGraph-Eval: Can LLMs Effectively Handle Ambiguous Graph Queries?
topic Databases
Artificial Intelligence
url https://arxiv.org/abs/2508.09631