# HARVE: Hacking-Aware Reward-Head Vector Editing for Robust Reward Models

arXiv: https://arxiv.org/abs/2606.03131 · HTML: https://mlsanity.com/paper/2606.03131/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Reward modeling and RLHF, one of 10 directions in LLM alignment / RLHF / preference optimisation.
- Builds on 29 of its 33 references that are in the map.
- First posted on arXiv 2 Jun 2026.

## Placed in

- LLM alignment / RLHF / preference optimisation / [Reward modeling and RLHF](https://mlsanity.com/alignment/reward-modeling-and-rlhf/)

## Builds on (most cited first, 29 of 29)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Learning to summarize from human feedback](https://mlsanity.com/paper/2009.01325/) (2020)
- [Representation Engineering: A Top-Down Approach to AI Transparency](https://mlsanity.com/paper/2310.01405/) (2023)
- [Scaling Laws for Reward Model Overoptimization](https://mlsanity.com/paper/2210.10760/) (2022)
- [Towards Understanding Sycophancy in Language Models](https://mlsanity.com/paper/2310.13548/) (2023)
- [Refusal in Language Models Is Mediated by a Single Direction](https://mlsanity.com/paper/2406.11717/) (2024)
- [Steering Language Models With Activation Engineering](https://mlsanity.com/paper/2308.10248/) (2023)
- [RAFT: Reward rAnked FineTuning for Generative Foundation Model Alignment](https://mlsanity.com/paper/2304.06767/) (2023)
- [RewardBench: Evaluating Reward Models for Language Modeling](https://mlsanity.com/paper/2403.13787/) (2024)
- [InternLM2 Technical Report](https://mlsanity.com/paper/2403.17297/) (2024)
- [Iterative Preference Learning from Human Feedback: Bridging Theory and Practice for RLHF under KL-Constraint](https://mlsanity.com/paper/2312.11456/) (2023)
- [LegalBench: A Collaboratively Built Benchmark for Measuring Legal Reasoning in Large Language Models](https://mlsanity.com/paper/2308.11462/) (2023)
- [Evaluating Large Language Models at Evaluating Instruction Following](https://mlsanity.com/paper/2310.07641/) (2023)
- [A Long Way to Go: Investigating Length Correlations in RLHF](https://mlsanity.com/paper/2310.03716/) (2023)
- [RLHF Workflow: From Reward Modeling to Online RLHF](https://mlsanity.com/paper/2405.07863/) (2024)
- [Reward Model Ensembles Help Mitigate Overoptimization](https://mlsanity.com/paper/2310.02743/) (2023)
- [Skywork-Reward-V2: Scaling Preference Data Curation via Human-AI Synergy](https://mlsanity.com/paper/2507.01352/) (2025)
- [Helping or Herding? Reward Model Ensembles Mitigate but do not Eliminate Reward Hacking](https://mlsanity.com/paper/2312.09244/) (2023)
- [RM-Bench: Benchmarking Reward Models of Language Models with Subtlety and Style](https://mlsanity.com/paper/2410.16184/) (2024)
- [Regularizing Hidden States Enables Learning Generalizable Reward Model for LLMs](https://mlsanity.com/paper/2406.10216/) (2024)
- [ODIN: Disentangled Reward Mitigates Hacking in RLHF](https://mlsanity.com/paper/2402.07319/) (2024)
- [OffsetBias: Leveraging Debiased Data for Tuning Evaluators](https://mlsanity.com/paper/2407.06551/) (2024)
- [How to Evaluate Reward Models for RLHF](https://mlsanity.com/paper/2410.14872/) (2024)
- [RRM: Robust Reward Model Training Mitigates Reward Hacking](https://mlsanity.com/paper/2409.13156/) (2024)
- [LEXam: Benchmarking Legal Reasoning on 340 Law Exams](https://mlsanity.com/paper/2505.12864/) (2025)
- [A Reasoning-Focused Legal Retrieval Benchmark](https://mlsanity.com/paper/2505.03970/) (2025)
- [ContractEval: Benchmarking LLMs for Clause-Level Legal Risk Identification in Commercial Contracts](https://mlsanity.com/paper/2508.03080/) (2025)
- [LLM Agents in Law: Taxonomy, Applications, and Challenges](https://mlsanity.com/paper/2601.06216/) (2026)
- [reward-lens: A Mechanistic Interpretability Library for Reward Models](https://mlsanity.com/paper/2604.26130/) (2026)

## Built on by (most cited first, 2 of 2)

- [BiasReducer: Adaptive Bias Mitigation for Reward Models](https://mlsanity.com/paper/2609.32720/) (2026)
- [RewardExplainer: Learning Reward Model Explanations from Counterfactual Preference Feedback](https://mlsanity.com/paper/2609.33989/) (2026)

## Abstract (arXiv)

Reward models are central to large language model (LLM) alignment, but they remain vulnerable to reward hacking. To evaluate reward-model robustness, we introduce RewardHackBench containing 13 reward-hacking patterns covering real life high-stakes domains and general settings, and we find severe failures on specific subcategories across eight reward models. To mitigate these failures, we propose HARVE, a training-free reward-head editing method for scalar reward models. Instead of fine-tuning the reward model, HARVE identifies a multi-directional hacking subspace from residual stream directions associated with selected hacking subcategories, and removes the component of the reward-head vector aligned with that subspace. This directly reduces the reward head's sensitivity to hacking-related features using only a small set of contrastive gold-hacked examples, without gradient updates or fine-tuning. Comprehensive experiments across eight reward models indicates that model improves hacking robustness, outperforms fine-tuning baselines, and preserves reward-models' general capability. Further analyses suggest that reward hacking is better captured as a multidimensional residual-space structure than by isolated surface cues.