ChatKBQA: A Generate-then-Retrieve Framework for Knowledge Base Question Answering with Fine-tuned Large Language Models

TL;DR

ChatKBQA introduces a generate-then-retrieve framework using fine-tuned large language models to improve knowledge base question answering, achieving state-of-the-art results by directly generating logical forms and refining retrieval.

Contribution

It presents a novel generate-then-retrieve approach that enhances KBQA performance and interpretability by combining LLMs with unsupervised retrieval methods.

Findings

Achieves new state-of-the-art on WebQSP and CWQ datasets.

Improves both generation accuracy and retrieval effectiveness.

Demonstrates a new paradigm for combining LLMs with knowledge graphs.

Abstract

Knowledge Base Question Answering (KBQA) aims to answer natural language questions over large-scale knowledge bases (KBs), which can be summarized into two crucial steps: knowledge retrieval and semantic parsing. However, three core challenges remain: inefficient knowledge retrieval, mistakes of retrieval adversely impacting semantic parsing, and the complexity of previous KBQA methods. To tackle these challenges, we introduce ChatKBQA, a novel and simple generate-then-retrieve KBQA framework, which proposes first generating the logical form with fine-tuned LLMs, then retrieving and replacing entities and relations with an unsupervised retrieval method, to improve both generation and retrieval more directly. Experimental results show that ChatKBQA achieves new state-of-the-art performance on standard KBQA datasets, WebQSP, and CWQ. This work can also be regarded as a new paradigm for combining LLMs with knowledge graphs (KGs) for interpretable and knowledge-required question answering. Our code is publicly available.