Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2509.19673 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912602386333696 |
|---|---|
| author | Aljohani, Ahmed Mollah, Anamul Haque Do, Hyunsook |
| author_facet | Aljohani, Ahmed Mollah, Anamul Haque Do, Hyunsook |
| contents | Assertion messages significantly enhance unit tests by clearly explaining the reasons behind test failures, yet they are frequently omitted by developers and automated test-generation tools. Despite recent advancements, Large Language Models (LLMs) have not been systematically evaluated for their ability to generate informative assertion messages. In this paper, we introduce an evaluation of four state-of-the-art Fill-in-the-Middle (FIM) LLMs - Qwen2.5-Coder-32B, Codestral-22B, CodeLlama-13B, and StarCoder - on a dataset of 216 Java test methods containing developer-written assertion messages. We find that Codestral-22B achieves the highest quality score of 2.76 out of 5 using a human-like evaluation approach, compared to 3.24 for manually written messages. Our ablation study shows that including descriptive test comments further improves Codestral's performance to 2.97, highlighting the critical role of context in generating clear assertion messages. Structural analysis demonstrates that all models frequently replicate developers' preferred linguistic patterns. We discuss the limitations of the selected models and conventional text evaluation metrics in capturing diverse assertion message structures. Our benchmark, evaluation results, and discussions provide an essential foundation for advancing automated, context-aware generation of assertion messages in test code. A replication package is available at https://doi.org/10.5281/zenodo.15293133 |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_19673 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Assertion Messages with Large Language Models (LLMs) for Code Aljohani, Ahmed Mollah, Anamul Haque Do, Hyunsook Software Engineering Assertion messages significantly enhance unit tests by clearly explaining the reasons behind test failures, yet they are frequently omitted by developers and automated test-generation tools. Despite recent advancements, Large Language Models (LLMs) have not been systematically evaluated for their ability to generate informative assertion messages. In this paper, we introduce an evaluation of four state-of-the-art Fill-in-the-Middle (FIM) LLMs - Qwen2.5-Coder-32B, Codestral-22B, CodeLlama-13B, and StarCoder - on a dataset of 216 Java test methods containing developer-written assertion messages. We find that Codestral-22B achieves the highest quality score of 2.76 out of 5 using a human-like evaluation approach, compared to 3.24 for manually written messages. Our ablation study shows that including descriptive test comments further improves Codestral's performance to 2.97, highlighting the critical role of context in generating clear assertion messages. Structural analysis demonstrates that all models frequently replicate developers' preferred linguistic patterns. We discuss the limitations of the selected models and conventional text evaluation metrics in capturing diverse assertion message structures. Our benchmark, evaluation results, and discussions provide an essential foundation for advancing automated, context-aware generation of assertion messages in test code. A replication package is available at https://doi.org/10.5281/zenodo.15293133 |
| title | Assertion Messages with Large Language Models (LLMs) for Code |
| topic | Software Engineering |
| url | https://arxiv.org/abs/2509.19673 |