Assertion-Aware Test Code Summarization with Large Language Models

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Mollah, Anamul Haque, Aljohani, Ahmed, Do, Hyunsook
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909895058522112
author Mollah, Anamul Haque
Aljohani, Ahmed
Do, Hyunsook
author_facet Mollah, Anamul Haque
Aljohani, Ahmed
Do, Hyunsook
contents Unit tests often lack concise summaries that convey test intent, especially in auto-generated or poorly documented codebases. Large Language Models (LLMs) offer a promising solution, but their effectiveness depends heavily on how they are prompted. Unlike generic code summarization, test-code summarization poses distinct challenges because test methods validate expected behavior through assertions rather than implementing functionality. This paper presents a new benchmark of 91 real-world Java test cases paired with developer-written summaries and conducts a controlled ablation study to investigate how test code-related components-such as the method under test (MUT), assertion messages, and assertion semantics-affect the performance of LLM-generated test summaries. We evaluate four code LLMs (Codex, Codestral, DeepSeek, and Qwen-Coder) across seven prompt configurations using n-gram metrics (BLEU, ROUGE-L, METEOR), semantic similarity (BERTScore), and LLM-based evaluation. Results show that prompting with assertion semantics improves summary quality by an average of 0.10 points (2.3%) over full MUT context (4.45 vs. 4.35) while requiring fewer input tokens. Codex and Qwen-Coder achieve the highest alignment with human-written summaries, while DeepSeek underperforms despite high lexical overlap. The replication package is publicly available at https://doi.org/10. 5281/zenodo.17067550
format Preprint
id arxiv_https___arxiv_org_abs_2511_06227
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Assertion-Aware Test Code Summarization with Large Language Models
Mollah, Anamul Haque
Aljohani, Ahmed
Do, Hyunsook
Software Engineering
Artificial Intelligence
Computational Engineering, Finance, and Science
Unit tests often lack concise summaries that convey test intent, especially in auto-generated or poorly documented codebases. Large Language Models (LLMs) offer a promising solution, but their effectiveness depends heavily on how they are prompted. Unlike generic code summarization, test-code summarization poses distinct challenges because test methods validate expected behavior through assertions rather than implementing functionality. This paper presents a new benchmark of 91 real-world Java test cases paired with developer-written summaries and conducts a controlled ablation study to investigate how test code-related components-such as the method under test (MUT), assertion messages, and assertion semantics-affect the performance of LLM-generated test summaries. We evaluate four code LLMs (Codex, Codestral, DeepSeek, and Qwen-Coder) across seven prompt configurations using n-gram metrics (BLEU, ROUGE-L, METEOR), semantic similarity (BERTScore), and LLM-based evaluation. Results show that prompting with assertion semantics improves summary quality by an average of 0.10 points (2.3%) over full MUT context (4.45 vs. 4.35) while requiring fewer input tokens. Codex and Qwen-Coder achieve the highest alignment with human-written summaries, while DeepSeek underperforms despite high lexical overlap. The replication package is publicly available at https://doi.org/10. 5281/zenodo.17067550
title Assertion-Aware Test Code Summarization with Large Language Models
topic Software Engineering
Artificial Intelligence
Computational Engineering, Finance, and Science
url https://arxiv.org/abs/2511.06227