arXiv cs.CL· Han Zhang, Langshi Zhou, Hanfang Yang·· 12 小时前AI 评分26
ArG：通过主动自我反思在知识图谱上学习检索与推理
Learning to Retrieve and Reason on Knowledge Graph through Active Self-Reflection
AI 导读
研究者提出面向知识图谱推理的主动自我反思框架 ArG，首次以端到端训练实现基于结构化图的迭代推理。模型用特殊 token 主动控制推理过程，实现按需检索和多维细粒度知识评估，生成的推理路径具备高可解释性。在知识图谱推理任务上，该模型优于现有基线，论文已被 CIKM 2026 的 LASS Workshop 接收。
正文 · 原文
Abstract:Extensive research has investigated the integration of large language models (LLMs) with knowledge graphs to enhance the reasoning process. However, understanding how models perform reasoning utilizing structured graph knowledge remains underexplored. Most existing approaches rely on LLMs or retrievers to make binary judgments regarding the utilization of knowledge, which is too coarse. Meanwhile, there is still a lack of feedback mechanisms for reflection and control throughout the entire reasoning path. This paper proposes an Active self-Reflection framework for knowledge Graph reasoning (ArG), introducing for the first time an end-to-end training approach to achieve iterative reasoning grounded on structured graphs. Within the framework, the model leverages special tokens to actively control the reasoning process, achieving on-demand retrieval and multi-dimensional, finer-grained knowledge evaluation. The reasoning paths generated by the model exhibit high interpretability, enabling deeper exploration of the model's understanding of structured knowledge. Ultimately, the proposed model achieves outstanding results compared to existing baselines in knowledge graph reasoning tasks.
| Comments: | 10 pages, 3 figures, 5 tables. Accepted at the LASS Workshop at CIKM 2026 |
| Subjects: | Computation and Language (cs.CL) |
| Cite as: | arXiv:2502.14932 [cs.CL] |
| (or arXiv:2502.14932v2 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2502.14932 arXiv-issued DOI via DataCite |
Submission history
From: Langshi Zhou [view email]
[v1]
Thu, 20 Feb 2025 06:38:48 UTC (973 KB)
[v2]
Fri, 16 Oct 2026 05:33:00 UTC (559 KB)
来源：arXiv cs.CL · arxiv.org