Simple and Effective Baselines for Code Summarisation Evaluation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Robinson, Jade, Kummerfeld, Jonathan K.
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910968496259072
author Robinson, Jade
Kummerfeld, Jonathan K.
author_facet Robinson, Jade
Kummerfeld, Jonathan K.
contents Code documentation is useful, but writing it is time-consuming. Different techniques for generating code summaries have emerged, but comparing them is difficult because human evaluation is expensive and automatic metrics are unreliable. In this paper, we introduce a simple new baseline in which we ask an LLM to give an overall score to a summary. Unlike n-gram and embedding-based baselines, our approach is able to consider the code when giving a score. This allows us to also make a variant that does not consider the reference summary at all, which could be used for other tasks, e.g., to evaluate the quality of documentation in code bases. We find that our method is as good or better than prior metrics, though we recommend using it in conjunction with embedding-based methods to avoid the risk of LLM-specific bias.
format Preprint
id arxiv_https___arxiv_org_abs_2505_19392
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Simple and Effective Baselines for Code Summarisation Evaluation
Robinson, Jade
Kummerfeld, Jonathan K.
Computation and Language
Artificial Intelligence
Software Engineering
68T50
I.2.7
Code documentation is useful, but writing it is time-consuming. Different techniques for generating code summaries have emerged, but comparing them is difficult because human evaluation is expensive and automatic metrics are unreliable. In this paper, we introduce a simple new baseline in which we ask an LLM to give an overall score to a summary. Unlike n-gram and embedding-based baselines, our approach is able to consider the code when giving a score. This allows us to also make a variant that does not consider the reference summary at all, which could be used for other tasks, e.g., to evaluate the quality of documentation in code bases. We find that our method is as good or better than prior metrics, though we recommend using it in conjunction with embedding-based methods to avoid the risk of LLM-specific bias.
title Simple and Effective Baselines for Code Summarisation Evaluation
topic Computation and Language
Artificial Intelligence
Software Engineering
68T50
I.2.7
url https://arxiv.org/abs/2505.19392