# few-shot
標記為「few-shot」的 9 篇文章
少樣本微調風險
與少樣本微調相關的安全風險——其中少量精心打造的樣本可顯著改變模型安全性質。
上下文學習利用
利用上下文學習進行提示詞注入、範例投毒與行為操弄的攻擊。
Few-Shot Injection Fundamentals
Craft few-shot examples that prime the model to follow attacker instructions in subsequent turns.
Lab: Few-Shot Manipulation Attacks
Craft fake few-shot examples that teach the model to bypass its safety training by demonstrating the desired 對抗性 behavior through fabricated conversation examples.
實驗室: Few-Shot Example 注入
動手lab exploring how injected few-shot examples can steer language model outputs toward attacker-chosen behaviors by exploiting in-context learning.
Few-Shot 操控
使用精心打造的上下文範例引導模型行為，包含 many-shot 越獄、被投毒的示範與基於範例的制約。
Few-Shot Injection
Using crafted few-shot examples within user input to steer LLM behavior toward unintended outputs, exploiting in-context learning to override safety training.
Few-Shot Example Poisoning 詳解
Poison few-shot examples in prompts to establish behavioral patterns that override system instructions.
Few-Shot 攻擊 Scaling Analysis
Detailed analysis of how few-shot examples scale to influence model behavior, from 2-shot to many-shot regime.