Interactive-KBQA: Multi-Turn Interactions for Knowledge Base Question Answering with Large Language Models

Guanming Xiong, Junwei Bao, Wen Zhao


Abstract
This study explores the realm of knowledge base question answering (KBQA). KBQA is considered a challenging task, particularly in parsing intricate questions into executable logical forms. Traditional semantic parsing (SP)-based methods require extensive data annotations, which result in significant costs. Recently, the advent of few-shot in-context learning, powered by large language models (LLMs), has showcased promising capabilities. Yet, fully leveraging LLMs to parse questions into logical forms in low-resource scenarios poses a substantial challenge. To tackle these hurdles, we introduce Interactive-KBQA, a framework designed to generate logical forms through direct interaction with knowledge bases (KBs). Within this framework, we have developed three generic APIs for KB interaction. For each category of complex question, we devised exemplars to guide LLMs through the reasoning processes. Our method achieves competitive results on the WebQuestionsSP, ComplexWebQuestions, KQA Pro, and MetaQA datasets with a minimal number of examples (shots). Importantly, our approach supports manual intervention, allowing for the iterative refinement of LLM outputs. By annotating a dataset with step-wise reasoning processes, we showcase our model’s adaptability and highlight its potential for contributing significant enhancements to the field.
Anthology ID:
2024.acl-long.569
Volume:
Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
Month:
August
Year:
2024
Address:
Bangkok, Thailand
Editors:
Lun-Wei Ku, Andre Martins, Vivek Srikumar
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
10561–10582
Language:
URL:
https://aclanthology.org/2024.acl-long.569
DOI:
Bibkey:
Cite (ACL):
Guanming Xiong, Junwei Bao, and Wen Zhao. 2024. Interactive-KBQA: Multi-Turn Interactions for Knowledge Base Question Answering with Large Language Models. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 10561–10582, Bangkok, Thailand. Association for Computational Linguistics.
Cite (Informal):
Interactive-KBQA: Multi-Turn Interactions for Knowledge Base Question Answering with Large Language Models (Xiong et al., ACL 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.acl-long.569.pdf