Personalization of Code Readability Evaluation Based on LLM Using Collaborative Filtering
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917855375654912 |
|---|---|
| author | Hiraki, Buntaro Hamamoto, Kensei Kimura, Ami Tsunoda, Masateru Tahir, Amjed Bennin, Kwabena Ebo Monden, Akito Nakasai, Keitaro |
| author_facet | Hiraki, Buntaro Hamamoto, Kensei Kimura, Ami Tsunoda, Masateru Tahir, Amjed Bennin, Kwabena Ebo Monden, Akito Nakasai, Keitaro |
| contents | Code readability is an important indicator of software maintenance as it can significantly impact maintenance efforts. Recently, LLM (large language models) have been utilized for code readability evaluation. However, readability evaluation differs among developers, so personalization of the evaluation by LLM is needed. This study proposes a method which calibrates the evaluation, using collaborative filtering. Our preliminary analysis suggested that the method effectively enhances the accuracy of the readability evaluation using LLMs. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2411_10583 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Personalization of Code Readability Evaluation Based on LLM Using Collaborative Filtering Hiraki, Buntaro Hamamoto, Kensei Kimura, Ami Tsunoda, Masateru Tahir, Amjed Bennin, Kwabena Ebo Monden, Akito Nakasai, Keitaro Software Engineering Code readability is an important indicator of software maintenance as it can significantly impact maintenance efforts. Recently, LLM (large language models) have been utilized for code readability evaluation. However, readability evaluation differs among developers, so personalization of the evaluation by LLM is needed. This study proposes a method which calibrates the evaluation, using collaborative filtering. Our preliminary analysis suggested that the method effectively enhances the accuracy of the readability evaluation using LLMs. |
| title | Personalization of Code Readability Evaluation Based on LLM Using Collaborative Filtering |
| topic | Software Engineering |
| url | https://arxiv.org/abs/2411.10583 |