Reward Models Can Improve Themselves: Reward-Guided Adversarial Failure Mode Discovery for Robust Reward Modeling

• URL: http://arxiv.org/abs/2507.06419v1
• Date: Tue, 08 Jul 2025 21:56:33 GMT
• Title: Reward Models Can Improve Themselves: Reward-Guided Adversarial Failure Mode Discovery for Robust Reward Modeling
• Authors: Pankayaraj Pathmanathan, Furong Huang,
• Abstract summary: We introduce REFORM, a self-improving reward modeling framework that enhances robustness by using the reward model itself to guide the generation of falsely scored responses.<n>We evaluate REFORM on two widely used preference datasets Anthropic Helpful Harmless (HH) and PKU Beavertails.
• Score: 27.11560841914813
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Reward modeling (RM), which captures human preferences to align large language models (LLMs), is increasingly employed in tasks such as model finetuning, response filtering, and ranking. However, due to the inherent complexity of human preferences and the limited coverage of available datasets, reward models often fail under distributional shifts or adversarial perturbations. Existing approaches for identifying such failure modes typically rely on prior knowledge about preference distributions or failure attributes, limiting their practicality in real-world settings where such information is unavailable. In this work, we propose a tractable, preference-distribution agnostic method for discovering reward model failure modes via reward guided controlled decoding. Building on this, we introduce REFORM, a self-improving reward modeling framework that enhances robustness by using the reward model itself to guide the generation of falsely scored responses. These adversarial examples are then used to augment the training data and patch the reward model's misaligned behavior. We evaluate REFORM on two widely used preference datasets Anthropic Helpful Harmless (HH) and PKU Beavertails and demonstrate that it significantly improves robustness without sacrificing reward quality. Notably, REFORM preserves performance both in direct evaluation and in downstream policy training, and further improves alignment quality by removing spurious correlations.

Related papers

• Fake it till You Make it: Reward Modeling as Discriminative Prediction [49.31309674007382]
  GAN-RM is an efficient reward modeling framework that eliminates manual preference annotation and explicit quality dimension engineering.<n>Our method trains the reward model through discrimination between a small set of representative, unpaired target samples.<n>Experiments demonstrate our GAN-RM's effectiveness across multiple key applications.
  arXiv  Detail & Related papers  (2025-06-16T17:59:40Z)
• Intra-Trajectory Consistency for Reward Modeling [67.84522106537274]
  We develop an intra-trajectory consistency regularization to enforce that adjacent processes with higher next-token generation probability maintain more consistent rewards.<n>We show that the reward model trained with the proposed regularization induces better DPO-aligned policies and achieves better best-of-N (BON) inference-time verification results.
  arXiv  Detail & Related papers  (2025-06-10T12:59:14Z)
• Regularizing Hidden States Enables Learning Generalizable Reward Model for LLMs [25.011675414622392]
  This study introduces a novel approach to enhance the reward model's generalization ability against distribution shifts. We retain the base model's language model head and incorporate a suite of text-generation losses to preserve the hidden states' text-generation capabilities. Our experimental results demonstrate that the introduced regularization technique markedly improves the accuracy of learned reward models.
  arXiv  Detail & Related papers  (2024-06-14T17:49:59Z)
• Robust Preference Optimization through Reward Model Distillation [68.65844394615702]
  Direct Preference Optimization (DPO) is a popular offline alignment method that trains a policy directly on preference data.<n>We analyze this phenomenon and use distillation to get a better proxy for the true preference distribution over generation pairs.<n>Our results show that distilling from such a family of reward models leads to improved robustness to distribution shift in preference annotations.
  arXiv  Detail & Related papers  (2024-05-29T17:39:48Z)
• RewardBench: Evaluating Reward Models for Language Modeling [100.28366840977966]
  We present RewardBench, a benchmark dataset and code-base for evaluation of reward models. The dataset is a collection of prompt-chosen-rejected trios spanning chat, reasoning, and safety. On the RewardBench leaderboard, we evaluate reward models trained with a variety of methods.
  arXiv  Detail & Related papers  (2024-03-20T17:49:54Z)
• InfoRM: Mitigating Reward Hacking in RLHF via Information-Theoretic Reward Modeling [66.3072381478251]
  Reward hacking, also termed reward overoptimization, remains a critical challenge. We propose a framework for reward modeling, namely InfoRM, by introducing a variational information bottleneck objective. We show that InfoRM's overoptimization detection mechanism is not only effective but also robust across a broad range of datasets.
  arXiv  Detail & Related papers  (2024-02-14T17:49:07Z)
• Secrets of RLHF in Large Language Models Part II: Reward Modeling [134.97964938009588]
  We introduce a series of novel methods to mitigate the influence of incorrect and ambiguous preferences in the dataset. We also introduce contrastive learning to enhance the ability of reward models to distinguish between chosen and rejected responses.
  arXiv  Detail & Related papers  (2024-01-11T17:56:59Z)
• A Baseline Analysis of Reward Models' Ability To Accurately Analyze Foundation Models Under Distribution Shift [2.2310395620011945]
  We evaluate how reward model performance is affected by distribution shift. We show novel calibration patterns and accuracy drops due to OOD prompts and responses. We adapt an OOD detection technique commonly used in classification to the reward model setting to detect these distribution shifts.
  arXiv  Detail & Related papers  (2023-11-21T18:41:26Z)
• RAFT: Reward rAnked FineTuning for Generative Foundation Model Alignment [32.752633250862694]
  Generative foundation models are susceptible to implicit biases that can arise from extensive unsupervised training data. We introduce a new framework, Reward rAnked FineTuning, designed to align generative models effectively.
  arXiv  Detail & Related papers  (2023-04-13T18:22:40Z)
• Exposing Shallow Heuristics of Relation Extraction Models with Challenge Data [49.378860065474875]
  We identify failure modes of SOTA relation extraction (RE) models trained on TACRED. By adding some of the challenge data as training examples, the performance of the model improves.
  arXiv  Detail & Related papers  (2020-10-07T21:17:25Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.