新闻
LLMs Don't Know What They Know: Benchmarking Temporal Self-Knowledge for Financial Backtesting
arXiv cs.AI · 发布于 · 阅读约3分钟
30秒读懂
- 发生了什么
- Researchers benchmarked LLMs' ability to accurately report what financial facts they know, finding self-reports significantly understate actual knowledge.
- 为何重要
- Matters for engineers building financial backtests or any system relying on LLM knowledge cutoffs to avoid data leakage.
- 注意
- Models claim ignorance on facts they answer correctly, and declared dates don't reliably prevent knowledge leakage beyond stated training windows.
- llm
- language model
- prompt
- edge
- benchmark
这条新闻背后的模式
- Temporal Knowledge Graph Memory
- Agentic Context Engineering (Evolving Playbook)
- Eval-Driven Development (Agent CI)
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。