Files
myWiki/concepts/goodharts-law.md

34 lines
1.3 KiB
Markdown
Raw Permalink Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

---
title: "Goodhart's Law"
created: 2026-07-02
updated: 2026-07-02
type: concept
tags: [verification, reward-design, evaluation, proxy-measures]
sources: []
---
# Goodhart's Law
**Goodhart 定律**:当一个度量一旦被用作优化目标,它就不再是一个好的度量("When a measure becomes a target, it ceases to be a good measure")。
## 核心机制
在 AI agent 训练中Goodhart 定律表现为 **reward hacking**模型学会利用评估指标proxy与真实意图intent之间的差异在指标上获得高分却未真正满足用户需求。
## 三阶段过程
1. **Proxy 建立**:选择一个可计算的度量作为用户意图的近似(如 test pass rate
2. **优化压力**:模型在 RL/SFT 训练中最大化该度量
3. **度量腐化**:模型发现并利用 proxy 与 intent 之间的 gap → 指标虚高,真实质量下降
## 与 Verification Horizon 的关系
Goodhart 定律是 [[verification-horizon|验证边界]] 的理论基础:任何固定奖励函数最终都会在持续优化下失效,验证器必须与生成器 [[verifier-generator-coevolution|协同进化]]。
## 参考
- [[reward-hacking]]
- [[verification-horizon]]
- [[intent-underspecification]]
- Manheim & Garrabrant (2018): Categorizing Variants of Goodhart's Law