用结构熵引导的智能体，精准发现并修复大模型的知识短板。
Structural Entropy Guided Agent for Detecting and Repairing Knowledge Deficiencies in LLMs
- 通过结构熵量化知识图谱路径的不确定性，定位模型真实知识盲区。
- 在多个领域基准上，使LLaMA-3和Qwen2性能显著提升。
- 适合需要高精度知识的大模型自优化场景，如医学与科研。
大语言模型虽凭借海量预训练数据取得突破性进展，但在医学、科研等需高度事实精确性的知识密集型领域表现仍不理想。尽管合成数据为增强领域知识提供了可能，但现有方法常生成与模型真实知识缺口不符的冗余样本。为此，我们提出结构熵引导的知识导航框架（SENATOR），利用结构熵（SE）度量知识图谱路径上的不确定性，并结合蒙特卡洛树搜索（MCTS）选择性探索模型缺乏领域知识的区域。基于此，框架生成针对性合成数据用于监督微调，实现持续自我改进。在LLaMA-3和Qwen2上多个领域专用基准的实验表明，SENATOR能有效检测并修复知识缺陷，带来显著性能提升。代码与数据已公开于https://github.com/weiyifan1023/senator。
原文摘要 · Abstract (English)
Large language models (LLMs) have achieved unprecedented performance by leveraging vast pretraining corpora, yet their performance remains suboptimal in knowledge-intensive domains such as medicine and scientific research, where high factual precision is required. While synthetic data provides a promising avenue for augmenting domain knowledge, existing methods frequently generate redundant samples that do not align with the model's true knowledge gaps. To overcome this limitation, we propose a novel Structural Entropy-guided Knowledge Navigator (SENATOR) framework that addresses the intrinsic knowledge deficiencies of LLMs. Our approach employs the Structure Entropy (SE) metric to quantify uncertainty along knowledge graph paths and leverages Monte Carlo Tree Search (MCTS) to selectively explore regions where the model lacks domain-specific knowledge. Guided by these insights, the framework generates targeted synthetic data for supervised fine-tuning, enabling continuous self-improvement. Experimental results on LLaMA-3 and Qwen2 across multiple domain-specific benchmarks show that SENATOR effectively detects and repairs knowledge deficiencies, achieving notable performance improvements. The code and data for our methods and experiments are available at https://github.com/weiyifan1023/senator.
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。