Debiasing Reward Models by Representation Learning with Guarantees

Recent alignment techniques, such as reinforcement learning from human feedback, have been widely adopted to align large language models with human preferences by learning and leveraging reward models. In practice, these models often exploit spurious correlations, involving, e.g., response length, discrimination, sycophancy, and conceptual bias, which is a problem that has received increasing attention. In this work, we propose a principled framework that mitigates these biases in reward models while preserving the underlying factors that reflect intended preferences. We first provide a formulation of the data-generating process, assuming that the observed data (e.g., text) is generated from both spurious and non-spurious latent variables. We show that, interestingly, these non-spurious latent variables can be theoretically identified from data, regardless of whether a surrogate for the spurious latent variables is available. This further inspires a practical method that uses variational inference to recover these variables and leverages them to train reward models. Experiments on synthetic and real-world datasets demonstrate that our method effectively mitigates spurious correlation issues and yields more robust reward models.