Instruction Fusion: Advancing Prompt Evolution through Hybridization
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2023
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917695751979008 |
|---|---|
| author | Guo, Weidong Yang, Jiuding Yang, Kaitong Li, Xiangyang Rao, Zhuwei Xu, Yu Niu, Di |
| author_facet | Guo, Weidong Yang, Jiuding Yang, Kaitong Li, Xiangyang Rao, Zhuwei Xu, Yu Niu, Di |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2312_15692 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Instruction Fusion: Advancing Prompt Evolution through Hybridization Guo, Weidong Yang, Jiuding Yang, Kaitong Li, Xiangyang Rao, Zhuwei Xu, Yu Niu, Di Artificial Intelligence 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. |
| title | Instruction Fusion: Advancing Prompt Evolution through Hybridization |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2312.15692 |