JPRQA: A Joint Progressive Reasoning Framework for Unsupervised KGQA With LLMs
TL;DR
JPRQA, a Joint Progressive Reasoning Framework for unsupervised KGQA with LLMs, is proposed, which decouples complex questions into sub‐questions to facilitate precise step‐by‐step reasoning over KG and enhances answer retrieval through collaborative path optimization, which integrates LLMs with RPR to refine and identify optimal retrieval paths for questions.
Abstract
The development of large language models (LLMs) has introduced innovative solutions to unsupervised knowledge graph question answering (KGQA). Existing methods typically retrieve answer entities by measuring semantic similarity between questions with reasoning paths in the KG. However, this paradigm struggles to capture the sequential dependencies embedded in the relational chains of complex questions. To bridge this gap, this paper proposes JPRQA, a Joint Progressive Reasoning Framework for unsupervised KGQA with LLMs, which decouples complex questions into sub‐questions to facilitate precise step‐by‐step reasoning over KG. Specifically, we designed a relation‐guided progressive reasoning (RPR) mechanism that leverages position‐aware relation predictors to model the sequential order of relations and perform step‐by‐step reasoning. Furthermore, we enhance answer retrieval through collaborative path optimization, which integrates LLMs with RPR to refine and identify optimal retrieval paths for questions. Experimental results demonstrate that JPRQA achieves an increase in F1 scores by 6.9 and 11.68 on the MetaQA (39,093 questions) and GrailQA (6763 questions) datasets, respectively, compared to other unsupervised methods.