新闻
Where Should a Document Live: Context, Representations, or Parameters?
arXiv cs.AI · 发布于 · 阅读约3分钟
30秒读懂
- 发生了什么
- Researchers compared three methods for giving LLMs access to new documents: context windows, fine-tuned parameters, and cached representations, finding representation-based methods most accurate.
- 为何重要
- Engineers building retrieval-augmented systems or knowledge-intensive applications need to choose between in-context, parametric, and representation injection approaches.
- 注意
- Representation methods show catastrophic forgetting on unrelated tasks, degrading performance by six percent generally and thirteen percent on coding benchmarks.
- llm
- language model
- context window
- fine-tun
- edge
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。