# Categorizing Variants of Goodhart's Law

arXiv: https://arxiv.org/abs/1803.04585 · HTML: https://mlsanity.com/paper/1803.04585/

## Key facts

- Cited by 149 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 13 Mar 2018.

## Built on by (most cited first, 30 of 149)

- [Scaling Laws for Reward Model Overoptimization](https://mlsanity.com/paper/2210.10760/) (2022)
- [Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2307.15217/) (2023)
- [GPT-NeoX-20B: An Open-Source Autoregressive Language Model](https://mlsanity.com/paper/2204.06745/) (2022)
- [Self-critiquing models for assisting human evaluators](https://mlsanity.com/paper/2206.05802/) (2022)
- [Unsolved Problems in ML Safety](https://mlsanity.com/paper/2109.13916/) (2021)
- [The Alignment Problem from a Deep Learning Perspective](https://mlsanity.com/paper/2209.00626/) (2022)
- [Defining and Characterizing Reward Hacking](https://mlsanity.com/paper/2209.13085/) (2022)
- [Disentangling Length from Quality in Direct Preference Optimization](https://mlsanity.com/paper/2403.19159/) (2024)
- [Scaling Laws for Reward Model Overoptimization in Direct Alignment Algorithms](https://mlsanity.com/paper/2406.02900/) (2024)
- [Truthful AI: Developing and governing AI that does not lie](https://mlsanity.com/paper/2110.06674/) (2021)
- [Is Power-Seeking AI an Existential Risk?](https://mlsanity.com/paper/2206.13353/) (2022)
- [Towards Guaranteed Safe AI: A Framework for Ensuring Robust and Reliable AI Systems](https://mlsanity.com/paper/2405.06624/) (2024)
- [Consequences of Misaligned AI](https://mlsanity.com/paper/2102.03896/) (2021)
- [Correlated Proxies: A New Definition and Improved Mitigation for Reward Hacking](https://mlsanity.com/paper/2403.03185/) (2024)
- [Goodhart's Law in Reinforcement Learning](https://mlsanity.com/paper/2310.09144/) (2023)
- [Style Outweighs Substance: Failure Modes of LLM Judges in Alignment Benchmarking](https://mlsanity.com/paper/2409.15268/) (2024)
- [Rethinking Reward Model Evaluation: Are We Barking up the Wrong Tree?](https://mlsanity.com/paper/2410.05584/) (2024)
- [The Trickle-down Impact of Reward (In-)consistency on RLHF](https://mlsanity.com/paper/2309.16155/) (2023)
- [SpecBench: Measuring Reward Hacking in Long-Horizon Coding Agents](https://mlsanity.com/paper/2605.21384/) (2026)
- [Law Informs Code: A Legal Informatics Approach to Aligning Artificial Intelligence with Humans](https://mlsanity.com/paper/2209.13020/) (2022)
- [Adaptation of Agentic AI: A Survey of Post-Training, Memory, and Skills](https://mlsanity.com/paper/2512.16301/) (2025)
- [The four-fifths rule is not disparate impact: a woeful tale of epistemic trespassing in algorithmic fairness](https://mlsanity.com/paper/2202.09519/) (2022)
- [A Philosophical Introduction to Language Models - Part II: The Way Forward](https://mlsanity.com/paper/2405.03207/) (2024)
- [Rethinking Reward Model Evaluation Through the Lens of Reward Overoptimization](https://mlsanity.com/paper/2505.12763/) (2025)
- [A taxonomic system for failure cause analysis of open source AI incidents](https://mlsanity.com/paper/2211.07280/) (2022)
- [On Goodhart's law, with an application to value alignment](https://mlsanity.com/paper/2410.09638/) (2024)
- [When LLM Judge Scores Look Good but Best-of-N Decisions Fail](https://mlsanity.com/paper/2603.12520/) (2026)
- [A Review of the Evidence for Existential Risk from AI via Misaligned Power-Seeking](https://mlsanity.com/paper/2310.18244/) (2023)
- [The Verification Horizon: No Silver Bullet for Coding Agent Rewards](https://mlsanity.com/paper/2606.26300/) (2026)
- [Collaboration Dynamics and Reliability Challenges of Multi-Agent LLM Systems in Finite Element Analysis](https://mlsanity.com/paper/2408.13406/) (2024)

## Abstract (arXiv)

There are several distinct failure modes for overoptimization of systems on the basis of metrics. This occurs when a metric which can be used to improve a system is used to an extent that further optimization is ineffective or harmful, and is sometimes termed Goodhart's Law. This class of failure is often poorly understood, partly because terminology for discussing them is ambiguous, and partly because discussion using this ambiguous terminology ignores distinctions between different failure modes of this general type. This paper expands on an earlier discussion by Garrabrant, which notes there are "(at least) four different mechanisms" that relate to Goodhart's Law. This paper is intended to explore these mechanisms further, and specify more clearly how they occur. This discussion should be helpful in better understanding these types of failures in economic regulation, in public policy, in machine learning, and in Artificial Intelligence alignment. The importance of Goodhart effects depends on the amount of power directed towards optimizing the proxy, and so the increased optimization power offered by artificial intelligence makes it especially critical for that field.