ToolSense:用于审计大语言模型中参数化工具知识的诊断框架
ToolSense: A Diagnostic Framework for Auditing Parametric Tool Knowledge in LLMs
中文简介
arXiv:2606.12451v1 公告类型:新 摘要:作为智能体部署在大型工具目录上的大型语言模型面临关键的工具检索瓶颈。由于基于嵌入的检索方法依赖于可能无法充分捕捉专用工具语义的紧凑编码器,参数化工具检索通过将每个工具编码为附加到LLM词汇表的虚拟标记来解决此问题,并经过两个阶段的微调(记忆阶段然后检索SFT),以使用LLM作为检索器,从而实现强大的性能。
English Summary
arXiv:2606.12451v1 Announce Type: new Abstract: Large language models deployed as agents over large tool catalogs face a critical tool-retrieval bottleneck. As embedding-based retrieval approaches rely on compact encoders that may under-capture specialized tool semantics, parametric tool retrieval addresses this by encoding each tool as a virtual token appended to the LLM vocabulary, fine-tuned in two stages (memorization then retrieval SFT) to use the LLM as a retriever, achieving strong perfor
内容来源
arXiv · Artificial Intelligence
本站仅提供摘要与索引,请在原始网站查看完整内容。