arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2503.00539cs.LGcs.AIcs.CL
收藏

具有人类反馈的分布鲁棒强化学习

Distributionally Robust Reinforcement Learning with Human Feedback

Debmalya Mandal, Paulius Sasnauskas, Goran Radanovic

AI总结:

本文提出一种分布鲁棒的强化学习方法,通过改进奖励基强化学习和直接偏好优化,提升模型在分布变化时的鲁棒性,实验显示在非分布任务中性能显著提升。

摘要:

强化学习从人类反馈(RLHF)已成为微调大型语言模型(LLMs)的主要方法。然而,现有RLHF方法缺乏鲁棒性,当下游任务与微调时使用的偏好数据集差异显著时,性能会下降。为此,我们引入了一种分布鲁棒的RLHF方法用于微调LLMs。我们的目标是确保微调后的模型在提示分布显著不同于微调期间遇到的分布时仍能保持性能。我们为两种流行的微调方法——(1)基于奖励的RLHF和(2)无奖励的DPO(直接偏好优化)——提出了分布鲁棒优化(DRO)版本。我们为两者提出了基于小批量梯度下降的算法,并在理论上证明了算法的收敛保证。随后,我们在非分布(OOD)任务上评估了我们的算法,首先在统一反馈数据集上训练模型,然后在两个不同的数据集上评估其性能。实验结果表明,我们的鲁棒训练在平均上提高了学习奖励模型的准确性,并在某些任务如推理上显著提高。此外,我们还显示,政策优化方法的鲁棒版本在非分布任务中同样提升了性能。

英文摘要:

Reinforcement learning from human feedback (RLHF) has evolved to be one of the main methods for fine-tuning large language models (LLMs). However, existing RLHF methods are non-robust, and their performance deteriorates if the downstream task differs significantly from the preference dataset used in fine-tuning. In order to mitigate this problem, we introduce a distributionally robust RLHF for fine-tuning LLMs. In particular, our goal is to ensure that a fine-tuned model retains its performance even when the distribution of prompts significantly differs from the distribution encountered during fine-tuning. We formulate distributionally robust optimization (DRO) version of two popular fine-tuning methods -- (1) reward-based RLHF and (2) reward-free DPO (direct preference optimization). We propose a minibatch gradient descent based algorithms for both of them, and theoretically prove convergence guarantees for the algorithms. Subsequently, we evaluate our algorithms on an out-of-distribution (OOD) task by first training the model on the Unified-Feedback dataset and evaluating its performance on two different datasets. The experimental results show that our robust training improves the accuracy of the learned reward models on average, and markedly on some tasks, such as reasoning. Furthermore, we show that the robust versions of policy optimization methods, similarly improve performance on OOD tasks.

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。

↑