Chain-of-Instructions: Compositional Instruction Tuning on Large Language Models
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866915089783717888 |
|---|---|
| author | Hayati, Shirley Anugrah Jung, Taehee Bodding-Long, Tristan Kar, Sudipta Sethy, Abhinav Kim, Joo-Kyung Kang, Dongyeop |
| author_facet | Hayati, Shirley Anugrah Jung, Taehee Bodding-Long, Tristan Kar, Sudipta Sethy, Abhinav Kim, Joo-Kyung Kang, Dongyeop |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_11532 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Chain-of-Instructions: Compositional Instruction Tuning on Large Language Models Hayati, Shirley Anugrah Jung, Taehee Bodding-Long, Tristan Kar, Sudipta Sethy, Abhinav Kim, Joo-Kyung Kang, Dongyeop Computation and Language 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. |
| title | Chain-of-Instructions: Compositional Instruction Tuning on Large Language Models |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2402.11532 |