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

TL;DR

Interactive-KBQA introduces a framework that enables large language models to interact with knowledge bases for multi-turn question answering, reducing data annotation needs and allowing iterative refinement for complex queries.

Contribution

The paper presents a novel interactive framework with APIs for KB interaction, guiding LLMs in low-resource scenarios and supporting manual refinement to improve KBQA performance.

Findings

Achieves competitive results on multiple KBQA datasets with few-shot learning.

Supports manual intervention for iterative output refinement.

Demonstrates adaptability through annotated reasoning process datasets.

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. However, 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.