KnowThyself: An Agentic Assistant for LLM Interpretability

作者：Suraj Prasai, Mengnan Du, Ying–Jun Angela Zhang, Fan Yang · 发表于：Proceedings of the AAAI Conference on Artificial Intelligence · 年份：2026 · DOI：10.1609/aaai.v40i48.42373 · 研究领域：Explainable Artificial Intelligence (XAI)、Artificial Intelligence in Healthcare and Education、Topic Modeling

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.