20260617:目前有914 页
This commit is contained in:
22
concepts/in-context-learning.md
Normal file
22
concepts/in-context-learning.md
Normal file
@@ -0,0 +1,22 @@
|
||||
---
|
||||
title: "上下文学习 (In-Context Learning)"
|
||||
created: 2026-06-03
|
||||
updated: 2026-06-03
|
||||
type: concept
|
||||
tags: [in-context-learning, LLM, prompting, few-shot]
|
||||
status: placeholder
|
||||
---
|
||||
|
||||
# 上下文学习 (In-Context Learning)
|
||||
|
||||
> ⚠️ 占位符页面 — 待完善
|
||||
|
||||
上下文学习(ICL)是 LLM 通过提示中的少量示例(few-shot)即可适应新任务的能力,无需参数更新。是 SFT 的轻量级替代方案。
|
||||
|
||||
研究表明,SFT 可能导致 LLM 的 ICL 能力下降——[[zhang-reconciling-sft-interaction-2026|Zhang et al. (2026)]] 的交互视角暗示,这可能是因为过拟合阶段涌现的噪声交互干扰了已有的泛化推理骨架。
|
||||
|
||||
## 相关概念
|
||||
|
||||
- [[supervised-fine-tuning|SFT]]
|
||||
- [[preserved-interactions-backbone|保留交互作为推理支柱]]
|
||||
- [[catastrophic-forgetting|灾难性遗忘]]
|
||||
Reference in New Issue
Block a user