arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 2510.23751cs.LGcs.AIstat.ML
收藏

基于有理论保证的表示学习消除奖励模型的偏差

Debiasing Reward Models by Representation Learning with Guarantees

Carnegie Mellon University(卡内基梅隆大学);Amazon(亚马逊);Mohamed bin Zayed University of Artificial Intelligence(穆罕默德·本·扎耶德智能大学)

Ignavier Ng, Patrick Blöbaum, Siddharth Bhandari, Kun Zhang, Shiva Kasiviswanathan

AI总结:

针对奖励模型易利用虚假相关性产生偏差的问题,提出基于表示学习的有理论保证的去偏框架,通过变分推断识别非虚假潜在变量训练奖励模型,实验验证其能有效去偏并提升鲁棒性。

摘要:

近期的对齐技术,例如基于人类反馈的强化学习,已被广泛用于通过学习和利用奖励模型,让大语言模型与人类偏好对齐。在实际应用中,这些模型往往会利用虚假相关性,涉及响应长度、歧视、谄媚和概念偏差等问题,该问题已受到越来越多的关注。在本研究中,我们提出了一个有理论依据的框架,可在保留反映预期偏好的潜在因素的同时,缓解奖励模型中的这些偏差。我们首先对数据生成过程进行了公式化表述,假设观测数据(例如文本)由虚假潜在变量和非虚假潜在变量共同生成。有趣的是,我们证明了无论是否存在虚假潜在变量的代理变量,这些非虚假潜在变量都可以从数据中得到理论识别。这进一步启发了一种实用方法:使用变分推断恢复这些变量,并利用它们来训练奖励模型。在合成数据集和真实数据集上的实验表明,我们的方法可有效缓解虚假相关性问题,生成更鲁棒的奖励模型。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑