用对话式助手让大模型解释自己，降低理解门槛。
KnowThyself: An Agentic Assistant for LLM Interpretability
- 通过对话界面整合多种解释工具，用户可自然提问
- 分步处理：重写问题→路由到专业模块→生成连贯解释
- 适合研究人员与工程师快速诊断大模型行为
我们开发了KnowThyself，一个用于大语言模型（LLM）可解释性的智能代理助手。现有工具虽提供有用洞察，但分散且依赖代码。KnowThyself将这些功能整合进基于聊天的界面，用户可上传模型、提出自然语言问题，并获得交互式可视化与引导式解释。核心由一个协调型LLM先重构用户问题，再由代理路由器将其分配至专用模块，最终输出上下文一致的解释。该设计降低了技术门槛，构建了一个可扩展的LLM检查平台。通过将全流程嵌入对话工作流，KnowThyself为可访问的LLM可解释性提供了坚实基础。
原文摘要 · Abstract (English)
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.
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。