Chain-of-Instructions: Compositional Instruction Tuning on Large Language Models
This addresses a bottleneck in instruction tuning for AI systems handling complex tasks, though it is incremental as it builds on existing instruction data.
The paper tackles the problem of large language models struggling with complex instructions composed of multiple subtasks by proposing chain-of-instructions (CoI) tuning, which improves generalization to unseen composite tasks like multilingual summarization.
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.