Abstract
It is imperative for Large language models (LLMs) to follow instructions with elaborate requirements (i.e. Complex Instructions Following). Yet, it remains under-explored how to enhance the ability of LLMs to follow complex instructions with multiple constraints. To bridge the gap, we initially study what training data is effective in enhancing complex constraints following abilities. We found that training LLMs with instructions containing multiple constraints enhances their understanding of complex instructions, especially those with lower complexity levels. The improvement can even generalize to compositions of out-of-domain constraints. Additionally, we further propose methods addressing how to obtain and utilize the effective training data. Finally, we conduct extensive experiments to prove the effectiveness of our methods in terms of overall performance, training efficiency, and generalization abilities under four settings.
Abstract (translated)
大语言模型(LLMs)必须遵循详细的指令(即复杂指令跟随),然而,尚未深入研究如何增强LLMs遵循复杂指令的多重约束的能力。为了弥合这个差距,我们首先研究了哪种训练数据可以有效增强LLMs对复杂指令的理解能力,尤其是那些复杂度较低的指令。我们发现,通过包含多个约束条件的指令进行训练,可以增强LLMs对复杂指令的理解能力,尤其是那些复杂度较低的指令。这种改进甚至可以扩展到跨域约束的组合。此外,我们进一步提出了如何获得和使用有效训练数据的方法。最后,我们通过四个设置进行广泛的实验,证明了我们方法在整体性能、训练效率和泛化能力方面的有效性。
URL
https://arxiv.org/abs/2404.15846