Instruction Matters: A Simple yet Effective Task Selection for Optimized Instruction Tuning of Specific Tasks

Changho Lee, Janghoon Han, Seonghyeon Ye, Stanley Jungkyu Choi, Honglak Lee, Kyunghoon Bae


Abstract
Instruction tuning has been proven effective in enhancing zero-shot generalization across various tasks and in improving the performance of specific tasks. For task-specific improvements, strategically selecting and training on related tasks that provide meaningful supervision is crucial, as this approach enhances efficiency and prevents performance degradation from learning irrelevant tasks. In this light, we introduce a simple yet effective task selection method that leverages instruction information alone to identify relevant tasks, optimizing instruction tuning for specific tasks. Our method is significantly more efficient than traditional approaches, which require complex measurements of pairwise transferability between tasks or the creation of data samples for the target task. Additionally, by aligning the model with the unique instructional template style of the meta-dataset, we enhance its ability to granularly discern relevant tasks, leading to improved overall performance. Experimental results demonstrate that training on a small set of tasks, chosen solely based on the instructions, results in substantial improvements in performance on benchmarks such as P3, Big-Bench, NIV2, and Big-Bench Hard. Significantly, these improvements surpass those achieved by prior task selection methods, highlighting the superiority of our approach.
Anthology ID:
2024.emnlp-main.1036
Volume:
Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing
Month:
November
Year:
2024
Address:
Miami, Florida, USA
Editors:
Yaser Al-Onaizan, Mohit Bansal, Yun-Nung Chen
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
18620–18642
Language:
URL:
https://aclanthology.org/2024.emnlp-main.1036
DOI:
Bibkey:
Cite (ACL):
Changho Lee, Janghoon Han, Seonghyeon Ye, Stanley Jungkyu Choi, Honglak Lee, and Kyunghoon Bae. 2024. Instruction Matters: A Simple yet Effective Task Selection for Optimized Instruction Tuning of Specific Tasks. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 18620–18642, Miami, Florida, USA. Association for Computational Linguistics.
Cite (Informal):
Instruction Matters: A Simple yet Effective Task Selection for Optimized Instruction Tuning of Specific Tasks (Lee et al., EMNLP 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.emnlp-main.1036.pdf