Existing approaches for aligning large language models with human preferences face a trade-off that requires a separate reward model (RM) for on-policy learning. In this paper, we present a novel alignment framework, SELF-JUDGE that (1) does on-policy learning and 2) is parameter efficient, as it does not require an additional RM for evaluating the samples for on-policy learning. To this end, we propose Judge-augmented Supervised Fine-Tuning (JSFT) to train a single model to act as both a policy and a judge. Specifically, we view the pairwise judgment task, choosing the better response from a response pair, as a special case of the instruction-following task. The resulting model can judge preferences of on-the-fly responses from current policy initialized from itself. Experimental results show the efficacy of SELF-JUDGE, outperforming baselines in preference benchmarks. We also show that the rejecting sampling by itself can improve performance further without an additional evaluator.

翻译：现有的大语言模型与人类偏好对齐方法面临一个权衡：需要单独的奖励模型进行策略学习。本文提出了一种新颖的对齐框架SELF-JUDGE，该框架（1）支持策略学习，且（2）具有参数效率，因为它不需要额外的奖励模型来评估策略学习的样本。为此，我们提出了法官增强监督微调方法，通过训练单一模型同时担任策略和法官角色。具体而言，我们将成对判断任务——从回答对中选择更优回答——视为指令跟随任务的特例。所得模型能够对基于自身初始化的当前策略生成的即时响应进行偏好判断。实验结果表明SELF-JUDGE框架的有效性，在偏好基准测试中优于基线方法。我们还证明，即使没有额外的评估器，仅通过拒绝采样也能进一步提升模型性能。