新闻
Keyword Harnesses Fail Open: A Cheap Diagnostic Ladder for Tool-Use Claims in Small Language Models
arXiv cs.AI · 发布于 · 阅读约3分钟
30秒读懂
- 发生了什么
- Keyword-matching benchmarks falsely credit small language models for tool use they cannot actually perform, requiring stricter diagnostics.
- 为何重要
- Matters when evaluating tool-use capabilities of small models under 1.2 billion parameters before deployment in production systems.
- 注意
- The proposed diagnostic ladder is cheap but requires careful implementation; seed sensitivity limits generalizability of some findings across different model architectures.
- language model
- small model
- tool use
- tool-use
- tokenizer
这条新闻背后的模式
每个模式都讲清楚技术如何运作、何时值得投入，以及在哪里会失效。
The Agent Architect
每周一个模式、一个权衡、一个生产事故案例。为构建智能体系统的人准备的每周简报。
每周一封邮件,一键退订。您的地址仅用于发送简报。