TaCIE: Enhancing Instruction Comprehension in Large Language Models through Task-Centred Instruction Evolution

Jiuding Yang, Shengyao Lu, Weidong Guo, Xiangyang Li, Kaitong Yang, Yu Xu, Di Niu


Abstract
The fine-tuning of Large Language Models (LLMs) specialized in code generation has seen notable advancements through the use of open-domain coding queries. Despite the successes, existing methodologies like Evol-Instruct encounter performance limitations, impeding further enhancements in code generation tasks. This paper examines the constraints of existing prompt evolution techniques and introduces a novel approach, Instruction Fusion (IF). IF innovatively combines two distinct prompts through a hybridization process, thereby enhancing the evolution of training prompts for code LLMs. Our experimental results reveal that the proposed novel method effectively addresses the shortcomings of prior methods, significantly improving the performance of Code LLMs across five code generation benchmarks, namely HumanEval, HumanEval+, MBPP, MBPP+ and MultiPL-E, which underscore the effectiveness of Instruction Fusion in advancing the capabilities of LLMs in code generation.
Anthology ID:
2025.coling-main.57
Volume:
Proceedings of the 31st International Conference on Computational Linguistics
Month:
January
Year:
2025
Address:
Abu Dhabi, UAE
Editors:
Owen Rambow, Leo Wanner, Marianna Apidianaki, Hend Al-Khalifa, Barbara Di Eugenio, Steven Schockaert
Venue:
COLING
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
855–869
Language:
URL:
https://aclanthology.org/2025.coling-main.57/
DOI:
Bibkey:
Cite (ACL):
Jiuding Yang, Shengyao Lu, Weidong Guo, Xiangyang Li, Kaitong Yang, Yu Xu, and Di Niu. 2025. TaCIE: Enhancing Instruction Comprehension in Large Language Models through Task-Centred Instruction Evolution. In Proceedings of the 31st International Conference on Computational Linguistics, pages 855–869, Abu Dhabi, UAE. Association for Computational Linguistics.
Cite (Informal):
TaCIE: Enhancing Instruction Comprehension in Large Language Models through Task-Centred Instruction Evolution (Yang et al., COLING 2025)
Copy Citation:
PDF:
https://aclanthology.org/2025.coling-main.57.pdf