KnowThyself: An Agentic Assistant for LLM Interpretability

📝 Original Info

• Title: KnowThyself: An Agentic Assistant for LLM Interpretability
• ArXiv ID: 2511.03878
• Date: 2025-11-05
• Authors: ** 정보가 제공되지 않음 (논문에 명시된 저자 정보를 확인해 주세요) **

📝 Abstract

We develop KnowThyself, an agentic assistant that advances large language model (LLM) interpretability. Existing tools provide useful insights but remain fragmented and code-intensive. KnowThyself consolidates these capabilities into a chat-based interface, where users can upload models, pose natural language questions, and obtain interactive visualizations with guided explanations. At its core, an orchestrator LLM first reformulates user queries, an agent router further directs them to specialized modules, and the outputs are finally contextualized into coherent explanations. This design lowers technical barriers and provides an extensible platform for LLM inspection. By embedding the whole process into a conversational workflow, KnowThyself offers a robust foundation for accessible LLM interpretability.

💡 Deep Analysis

📄 Full Content

Reference