paper-with-me

Papers

Structural Entropy Guided Agent for Detecting and Repairing Knowledge Deficiencies in LLMs

2025-05-12 · Yifan Wei, Xiaoyan Yu, Tengfei Pan, Angsheng Li, Li Du

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.

📄 PDF Abstract BibTeX arXiv:2505.07184

Code (1)

weiyifan1023/senator 공식 구현 pytorch

Tasks

AI AgentKnowledge DistillationKnowledge GraphsReinforcement LearningSynthetic Data Generation

Methods 이 논문이 사용한 방법론

ALIGN In the ALIGN method, visual and language representations are jointly trained from noisy image alt-text data. The image and text encoders are learned via contrastive loss…

Similar Papers 제목 키워드 기반

Counterexample-Guided Repair of Reinforcement Learning Systems Using Safety Critics

2024-05-24 · David Boetius, Stefan Leue

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 Learning

Completing and Debugging Ontologies: state of the art and challenges

2019-08-08 · Patrick Lambrix

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

2026-01-07 · Yifan Wei, Li Du, Xiaoyan Yu, Yang Feng 외 arxiv

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

2022-10-21 · Zeyu Tang, Nan Yang, Simon Walsh, Guang Yang

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 …

PrognosisSegmentation

Planning Task Shielding: Detecting and Repairing Flaws in Planning Tasks through Turning them Unsolvable

2026-04-08 · Alberto Pozanco, Marianela Morales, Pietro Totis, Daniel Borrajo arxiv

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…