iQUEST通过迭代提问提升知识库问答的推理准确性。
iQUEST: An Iterative Question-Guided Framework for Knowledge Base Question Answering
- 用迭代分解问题的方式引导推理路径，避免混乱。
- 结合图神经网络前瞻2跳邻居信息，增强多跳推理能力。
- 在4个数据集和4个大模型上均表现更优，适合复杂问答场景。
大型语言模型在知识密集型任务中常出现事实性错误。引入外部知识资源（尤其是知识图谱）可提供透明且可更新的推理基础。知识库问答（KBQA）是实现这一目标的核心，尤其适用于复杂的多跳查询。然而，多跳推理面临两大挑战：(1) 保持连贯的推理路径；(2) 避免过早丢弃关键的多跳连接。为此，我们提出iQUEST，一种基于问题引导的KBQA框架，通过迭代将复杂问题分解为更简单的子问题，确保推理过程结构化且聚焦。此外，我们在每一步推理中引入图神经网络（GNN），前瞻并融合2跳邻域信息，强化推理能力，使模型能更有效地探索可行路径。大量实验表明，iQUEST在四个基准数据集和四种LLM上均实现了稳定提升。代码已公开于：https://github.com/Wangshuaiia/iQUEST。
原文摘要 · Abstract (English)
Large Language Models (LLMs) excel in many natural language processing tasks but often exhibit factual inconsistencies in knowledge-intensive settings. Integrating external knowledge resources, particularly knowledge graphs (KGs), provides a transparent and updatable foundation for more reliable reasoning. Knowledge Base Question Answering (KBQA), which queries and reasons over KGs, is central to this effort, especially for complex, multi-hop queries. However, multi-hop reasoning poses two key challenges: (1)~maintaining coherent reasoning paths, and (2)~avoiding prematurely discarding critical multi-hop connections. To tackle these challenges, we introduce iQUEST, a question-guided KBQA framework that iteratively decomposes complex queries into simpler sub-questions, ensuring a structured and focused reasoning trajectory. Additionally, we integrate a Graph Neural Network (GNN) to look ahead and incorporate 2-hop neighbor information at each reasoning step. This dual approach strengthens the reasoning process, enabling the model to explore viable paths more effectively. Detailed experiments demonstrate the consistent improvement delivered by iQUEST across four benchmark datasets and four LLMs. The code is publicly available at: https://github.com/Wangshuaiia/iQUEST.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。