Reinforcement learning has seen wide success in finetuning large language models to better align with instructions via human feedback. The so-called algorithm, Reinforcement Learning with Human Feedback (RLHF) demonstrates impressive performance on the GPT series models. However, the underlying Reinforcement Learning (RL) algorithm is complex and requires an additional training pipeline for reward and value networks. In this paper, we consider an alternative approach: converting feedback to instruction by relabeling the original one and training the model for better alignment in a supervised manner. Such an algorithm doesn't require any additional parameters except for the original language model and maximally reuses the pretraining pipeline. To achieve this, we formulate instruction alignment problem for language models as a goal-reaching problem in decision making. We propose Hindsight Instruction Relabeling (HIR), a novel algorithm for aligning language models with instructions. The resulting two-stage algorithm shed light to a family of reward-free approaches that utilize the hindsightly relabeled instructions based on feedback. We evaluate the performance of HIR extensively on 12 challenging BigBench reasoning tasks and show that HIR outperforms the baseline algorithms and is comparable to or even surpasses supervised finetuning.

本文提出一种基于回顾性指令重新标注的新算法 HIR，通过训练模型使其与指令更好地对齐，以解决语言模型中指令对齐的问题，并从12个挑战性的 BigBench 推理任务中的表现证明 HIR 优于基线算法，并且即使超过了有监督微调。

回顾智慧让语言模型成为更好的指令跟随者