כתבה
arXiv cs.CL ·
כשכלים נכנסים לדרך: השפעת זמינות כלים לא-נחוצים על תשובות LLM
When Tools Get in the Way: The Effect of Unnecessary Tool Availability on LLM Answering
מחקר חדש מצא כי זמינות כלים לא-נחוצים פוגעת ביכולת של LLMs לתת תשובות. המחקר נערך על 6 LLMs, כולל Gemini, LangGraph ו-GPT.
תקציר מקורי באנגליתarXiv:2609.14157v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly deployed with external tools that extend what they can do beyond their own knowledge. Tools help on tasks that need external information, but their availability may also change how a model handles questions that do not need them. Prior work has mostly asked whether models select and use tools appropriately; whether an unnecessary tool changes the correctness of answers has received less attention. We ask whether making a related but unnecessary tool available affects a model's ability to answer from its own knowledge, and whether a preceding tool interaction changes this behaviour. We construct 500 query pairs across 10 knowledge domains. Each pair consists of a tool query, which needs the domain'
קרא במקור המקורי
arxiv.org
פתח כתבה מקורית