用大模型+知识图谱迭代探索，解决需要常识推理的复杂问答问题
ARK-V1: An LLM-Agent for Knowledge Graph Question Answering Requiring Commonsense Reasoning
- 通过迭代式图遍历，让大模型逐步搜索知识图谱
- 在CoLoTa数据集上准确率显著高于传统链式推理方法
- 大模型越大效果越好，适合长尾实体和复杂推理场景
大型语言模型虽具备强大推理能力，但在涉及特定领域知识的问题上常因内部知识不足、过时或错误而表现不佳。知识图谱提供结构化外部知识，但其复杂性和多跳推理需求使融合困难。我们提出ARK-V1，一种简单的知识图谱智能体，通过迭代探索图谱来回答自然语言问题。我们在CoLoTa数据集上评估了多个未微调的前沿大模型作为ARK-V1的主干模型，该数据集要求结合知识图谱与常识推理，且涉及长尾实体。ARK-V1在条件准确率上显著优于链式思维基线，更大的主干模型展现出更优的覆盖范围、正确性和稳定性。
原文摘要 · Abstract (English)
Large Language Models (LLMs) show strong reasoning abilities but rely on internalized knowledge that is often insufficient, outdated, or incorrect when trying to answer a question that requires specific domain knowledge. Knowledge Graphs (KGs) provide structured external knowledge, yet their complexity and multi-hop reasoning requirements make integration challenging. We present ARK-V1, a simple KG-agent that iteratively explores graphs to answer natural language queries. We evaluate several not fine-tuned state-of-the art LLMs as backbones for ARK-V1 on the CoLoTa dataset, which requires both KG-based and commonsense reasoning over long-tail entities. ARK-V1 achieves substantially higher conditional accuracies than Chain-of-Thought baselines, and larger backbone models show a clear trend toward better coverage, correctness, and stability.
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。