Interactive-KBQA：基于大语言模型的知识库问答多轮交互
Interactive-KBQA: Multi-Turn Interactions for Knowledge Base Question Answering with Large Language Models
AI总结：
本文提出 Interactive-KBQA 框架，通过设计三类知识库交互 API 和分步推理示例，引导大语言模型在少样本低资源场景下将复杂问题解析为逻辑形式，并支持人工迭代优化，在多个 KBQA 数据集上取得有竞争力的结果。
摘要：
本研究探讨了知识库问答（KBQA）领域。KBQA 被认为是一项具有挑战性的任务，尤其是在将复杂问题解析为可执行逻辑形式方面。传统的基于语义解析（SP）的方法需要大量的数据标注，从而带来显著的成本。近年来，由大语言模型（LLM）驱动的少样本上下文学习展现出令人期待的能力。然而，在低资源场景下，充分利用 LLM 将问题解析为逻辑形式仍然构成重大挑战。为应对这些困难，我们提出了 Interactive-KBQA，这是一个旨在通过与知识库（KB）直接交互来生成逻辑形式的框架。在该框架内，我们开发了三个用于 KB 交互的通用 API。针对每一类复杂问题，我们设计了示例来引导 LLM 完成推理过程。我们的方法在 WebQuestionsSP、ComplexWebQuestions、KQA Pro 和 MetaQA 数据集上以极少的示例数量（shots）取得了具有竞争力的结果。重要的是，我们的方法支持人工干预，允许对 LLM 输出进行迭代优化。通过标注一个带有逐步推理过程的数据集，我们展示了模型的适应性，并凸显了其为该领域带来显著改进的潜力。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
