Humans often interact with large language models (LLMs) in multi-turn interaction to obtain desired answers or more information. However, most existing studies overlook the multi-turn instruction following ability of LLMs, in terms of training dataset, training method, and evaluation benchmark. In this paper, we introduce Parrot, a solution aiming to enhance multi-turn instruction following for LLMs. First, we introduce an efficient but effective method for collecting multi-turn instructions that feature human-like queries, such as anaphora and ellipsis. Second, we propose a context-aware preference optimization strategy to further enhance LLMs for complex queries in multi-turn interaction. Moreover, to quantitatively evaluate LLMs in multi-turn instruction following, we manually build a multi-turn benchmark derived from existing ones. Extensive experiments show that Parrot improves current LLMs by up to 7.2% in multi-turn instruction following. Our dataset and codes will be open-sourced to facilitate future research.
@article{arxiv.2310.07301,
title = {Parrot: Enhancing Multi-Turn Instruction Following for Large Language Models},
author = {Yuchong Sun and Che Liu and Kun Zhou and Jinwen Huang and Ruihua Song and Wayne Xin Zhao and Fuzheng Zhang and Di Zhang and Kun Gai},
journal= {arXiv preprint arXiv:2310.07301},
year = {2024}
}