TrustUQA: A Trustful Framework for Unified Structured Data Question Answering

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhang, Wen, Jin, Long, Zhu, Yushan, Chen, Jiaoyan, Huang, Zhiwei, Wang, Junjie, Hua, Yin, Liang, Lei, Chen, Huajun
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917867774017536
author Zhang, Wen
Jin, Long
Zhu, Yushan
Chen, Jiaoyan
Huang, Zhiwei
Wang, Junjie
Hua, Yin
Liang, Lei
Chen, Huajun
author_facet Zhang, Wen
Jin, Long
Zhu, Yushan
Chen, Jiaoyan
Huang, Zhiwei
Wang, Junjie
Hua, Yin
Liang, Lei
Chen, Huajun
contents Natural language question answering (QA) over structured data sources such as tables and knowledge graphs have been widely investigated, especially with Large Language Models (LLMs) in recent years. The main solutions include question to formal query parsing and retrieval-based answer generation. However, current methods of the former often suffer from weak generalization, failing to dealing with multi-types of sources, while the later is limited in trustfulness. In this paper, we propose TrustUQA, a trustful QA framework that can simultaneously support multiple types of structured data in a unified way. To this end, it adopts an LLM-friendly and unified knowledge representation method called Condition Graph(CG), and uses an LLM and demonstration-based two-level method for CG querying. For enhancement, it is also equipped with dynamic demonstration retrieval. We have evaluated TrustUQA with 5 benchmarks covering 3 types of structured data. It outperforms 2 existing unified structured data QA methods. In comparison with the baselines that are specific to one data type, it achieves state-of-the-art on 2 of the datasets. Further more, we have demonstrated the potential of our method for more general QA tasks, QA over mixed structured data and QA across structured data. The code is available at https://github.com/zjukg/TrustUQA.
format Preprint
id arxiv_https___arxiv_org_abs_2406_18916
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle TrustUQA: A Trustful Framework for Unified Structured Data Question Answering
Zhang, Wen
Jin, Long
Zhu, Yushan
Chen, Jiaoyan
Huang, Zhiwei
Wang, Junjie
Hua, Yin
Liang, Lei
Chen, Huajun
Computation and Language
Artificial Intelligence
Natural language question answering (QA) over structured data sources such as tables and knowledge graphs have been widely investigated, especially with Large Language Models (LLMs) in recent years. The main solutions include question to formal query parsing and retrieval-based answer generation. However, current methods of the former often suffer from weak generalization, failing to dealing with multi-types of sources, while the later is limited in trustfulness. In this paper, we propose TrustUQA, a trustful QA framework that can simultaneously support multiple types of structured data in a unified way. To this end, it adopts an LLM-friendly and unified knowledge representation method called Condition Graph(CG), and uses an LLM and demonstration-based two-level method for CG querying. For enhancement, it is also equipped with dynamic demonstration retrieval. We have evaluated TrustUQA with 5 benchmarks covering 3 types of structured data. It outperforms 2 existing unified structured data QA methods. In comparison with the baselines that are specific to one data type, it achieves state-of-the-art on 2 of the datasets. Further more, we have demonstrated the potential of our method for more general QA tasks, QA over mixed structured data and QA across structured data. The code is available at https://github.com/zjukg/TrustUQA.
title TrustUQA: A Trustful Framework for Unified Structured Data Question Answering
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2406.18916