RJE框架让小模型高效答知识图谱问题，少调用大模型
RJE: A Retrieval-Judgment-Exploration Framework for Efficient Knowledge Graph Question Answering with LLMs
- 分三步：找推理路径、判断是否够、不够就补证据
- 3B/8B小模型不微调也能达顶尖水平，比传统方法少用60%以上调用
- 适合资源有限但想用大模型能力的开发者
知识图谱问答（KGQA）旨在利用知识图谱回答自然语言问题。近期研究借助大语言模型（LLMs）提升推理能力，但面临两大挑战：基于检索的方法受限于召回信息质量，而基于智能体的方法过度依赖专有大模型。为此，本文提出检索-判断-探索（RJE）框架，通过检索优化的推理路径、评估其充分性，并在必要时条件性地探索额外证据。RJE引入三项专用辅助模块：推理路径排序、问题分解与检索增强探索，使小型开放模型（如3B和8B参数量）无需微调即可实现竞争力表现。实验表明，使用专有大模型（如GPT-4o-mini）时，RJE优于现有基线；同时相比基于智能体的方法，显著减少约60%以上的模型调用次数与令牌消耗，带来显著效率提升。
原文摘要 · Abstract (English)
Knowledge graph question answering (KGQA) aims to answer natural language questions using knowledge graphs. Recent research leverages large language models (LLMs) to enhance KGQA reasoning, but faces limitations: retrieval-based methods are constrained by the quality of retrieved information, while agent-based methods rely heavily on proprietary LLMs. To address these limitations, we propose Retrieval-Judgment-Exploration (RJE), a framework that retrieves refined reasoning paths, evaluates their sufficiency, and conditionally explores additional evidence. Moreover, RJE introduces specialized auxiliary modules enabling small-sized LLMs to perform effectively: Reasoning Path Ranking, Question Decomposition, and Retriever-assisted Exploration. Experiments show that our approach with proprietary LLMs (such as GPT-4o-mini) outperforms existing baselines while enabling small open-source LLMs (such as 3B and 8B parameters) to achieve competitive results without fine-tuning LLMs. Additionally, RJE substantially reduces the number of LLM calls and token usage compared to agent-based methods, yielding significant efficiency improvements.
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。