KARPA：一种免训练地将知识图谱作为参考以适应大语言模型推理路径聚合的方法
KARPA: A Training-free Method of Adapting Knowledge Graph as References for Large Language Model's Reasoning Path Aggregation
AI总结：
KARPA框架利用LLM全局规划能力进行关系路径预规划、语义匹配与路径推理，免训练地实现高效准确的知识图谱问答。
摘要：
大语言模型（LLMs）在各类任务中表现出卓越性能，但常受幻觉和知识时效性问题影响。利用知识图谱（KGs）作为外部知识源已成为一种可行的解决方案，然而现有基于LLM的知识图谱问答（KGQA）方法往往受限于在知识图谱上的逐步决策，限制了LLM的全局规划与推理能力，或者需要对特定知识图谱进行微调或预训练。为应对这些挑战，我们提出知识图谱辅助推理路径聚合（Knowledge graph Assisted Reasoning Path Aggregation，KARPA），这是一个利用LLM全局规划能力实现高效且准确的知识图谱推理的新框架。KARPA分三步运行：利用LLM的全局规划能力预先规划关系路径，通过嵌入模型匹配语义相关路径，并在这些路径上进行推理以生成答案。与现有KGQA方法不同，KARPA避免了逐步遍历，无需额外训练，并且可适配各种LLM架构。大量实验结果表明，KARPA在KGQA任务中达到了最先进的性能，同时具备高效率和准确性。我们的代码将在Github上公开。
英文摘要：
Large language models (LLMs) demonstrate exceptional performance across a variety of tasks, yet they are often affected by hallucinations and the timeliness of knowledge. Leveraging knowledge graphs (KGs) as external knowledge sources has emerged as a viable solution, but existing methods for LLM-based knowledge graph question answering (KGQA) are often limited by step-by-step decision-making on KGs, restricting the global planning and reasoning capabilities of LLMs, or they require fine-tuning or pre-training on specific KGs. To address these challenges, we propose Knowledge graph Assisted Reasoning Path Aggregation (KARPA), a novel framework that harnesses the global planning abilities of LLMs for efficient and accurate KG reasoning. KARPA operates in three steps: pre-planning relation paths using the LLM's global planning capabilities, matching semantically relevant paths via an embedding model, and reasoning over these paths to generate answers. Unlike existing KGQA methods, KARPA avoids stepwise traversal, requires no additional training, and is adaptable to various LLM architectures. Extensive experimental results show that KARPA achieves state-of-the-art performance in KGQA tasks, delivering both high efficiency and accuracy. Our code will be available on Github.
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。
