Structural Entropy Guided Agent for Detecting and Repairing Knowledge Deficiencies in LLMs
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.
Code (1)
Tasks
AI AgentKnowledge DistillationKnowledge GraphsReinforcement LearningSynthetic Data GenerationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Counterexample-Guided Repair of Reinforcement Learning Systems Using Safety Critics
Naively trained Deep Reinforcement Learning agents may fail to satisfy vital safety constraints. To avoid costly retraining, we may desire to repair a previously trained reinforcement learning agent to obviate unsafe beh…
Deep Reinforcement Learningreinforcement-learningReinforcement LearningCompleting and Debugging Ontologies: state of the art and challenges
As semantically-enabled applications require high-quality ontologies, developing and maintaining ontologies that are as correct and complete as possible is an important although difficult task in ontology engineering. A …
Towards Compositional Generalization of LLMs via Skill Taxonomy Guided Data Synthesis
Large Language Models (LLMs) and agent-based systems often struggle with compositional generalization due to a data bottleneck in which complex skill combinations follow a long-tailed, power-law distribution, limiting bo…
Adversarial Transformer for Repairing Human Airway Segmentation
Discontinuity in the delineation of peripheral bronchioles hinders the potential clinical application of automated airway segmentation models. Moreover, the deployment of such models is limited by the data heterogeneity …
PrognosisSegmentationPlanning Task Shielding: Detecting and Repairing Flaws in Planning Tasks through Turning them Unsolvable
Most research in planning focuses on generating a plan to achieve a desired set of goals. However, a goal specification can also be used to encode a property that should never hold, allowing a planner to identify a trace…