Chain-of-Instructions: Compositional Instruction Tuning on Large Language Models
Shirley Anugrah Hayati, Taehee Jung, Tristan Bodding-Long, Sudipta Kar, Abhinav Sethy, Joo-Kyung Kim, Dongyeop Kang
Abstract
Fine-tuning large language models (LLMs) with a collection of large and diverse instructions has improved the model’s generalization to different tasks, even for unseen tasks. However, most existing instruction datasets include only single instructions, and they struggle to follow complex instructions composed of multiple subtasks. In this work, we propose a novel concept of compositional instructions called chain-of-instructions (CoI), where the output of one instruction becomes an input for the next like a chain. Unlike the conventional practice of solving single instruction tasks, our proposed method encourages a model to solve each subtask step by step until the final answer is reached. CoI-tuning (i.e., fine-tuning with CoI instructions) improves the model’s ability to handle instructions composed of multiple subtasks as well as unseen composite tasks such as multilingual summarization. Overall, our study find that simple CoI tuning of existing instruction data can provide consistent generalization to solve more complex, unseen, and longer chains of instructions.
BibTeX
@article{Hayati_Jung_Bodding-Long_Kar_Sethy_Kim_Kang_2025, title={Chain-of-Instructions: Compositional Instruction Tuning on Large Language Models}, volume={39}, url={https://ojs.aaai.org/index.php/AAAI/article/view/34574}, DOI={10.1609/aaai.v39i22.34574}, abstractNote={Fine-tuning large language models (LLMs) with a collection of large and diverse instructions has improved the model’s generalization to different tasks, even for unseen tasks. However, most existing instruction datasets include only single instructions, and they struggle to follow complex instructions composed of multiple subtasks. In this work, we propose a novel concept of compositional instructions called chain-of-instructions (CoI), where the output of one instruction becomes an input for the next like a chain. Unlike the conventional practice of solving single instruction tasks, our proposed method encourages a model to solve each subtask step by step until the final answer is reached. CoI-tuning (i.e., fine-tuning with CoI instructions) improves the model’s ability to handle instructions composed of multiple subtasks as well as unseen composite tasks such as multilingual summarization. Overall, our study find that simple CoI tuning of existing instruction data can provide consistent generalization to solve more complex, unseen, and longer chains of instructions.}, number={22}, journal={Proceedings of the AAAI Conference on Artificial Intelligence}, author={Hayati, Shirley Anugrah and Jung, Taehee and Bodding-Long, Tristan and Kar, Sudipta and Sethy, Abhinav and Kim, Joo-Kyung and Kang, Dongyeop}, year={2025}, month={Apr.}, pages={24005-24013} }