Progressive Code Integration for Abstractive Bug Report Summarization
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909933806551040 |
|---|---|
| author | Karim, Shaira Sadia Rahim, Abrar Mahmud Alam, Lamia Tashdeed, Ishmam Lota, Lutfun Nahar Kamal, Md. Abu Raihan M. Hossain, Md. Azam |
| author_facet | Karim, Shaira Sadia Rahim, Abrar Mahmud Alam, Lamia Tashdeed, Ishmam Lota, Lutfun Nahar Kamal, Md. Abu Raihan M. Hossain, Md. Azam |
| contents | Bug reports are often unstructured and verbose, making it challenging for developers to efficiently comprehend software issues. Existing summarization approaches typically rely on surface-level textual cues, resulting in incomplete or redundant summaries, and they frequently ignore associated code snippets, which are essential for accurate defect diagnosis. To address these limitations, we propose a progressive code-integration framework for LLM-based abstractive bug report summarization. Our approach incrementally incorporates long code snippets alongside textual content, overcoming standard LLM context window constraints and producing semantically rich summaries. Evaluated on four benchmark datasets using eight LLMs, our pipeline outperforms extractive baselines by 7.5%-58.2% and achieves performance comparable to state-of-the-art abstractive methods, highlighting the benefits of jointly leveraging textual and code information for enhanced bug comprehension. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_00325 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Progressive Code Integration for Abstractive Bug Report Summarization Karim, Shaira Sadia Rahim, Abrar Mahmud Alam, Lamia Tashdeed, Ishmam Lota, Lutfun Nahar Kamal, Md. Abu Raihan M. Hossain, Md. Azam Software Engineering Artificial Intelligence Computation and Language Bug reports are often unstructured and verbose, making it challenging for developers to efficiently comprehend software issues. Existing summarization approaches typically rely on surface-level textual cues, resulting in incomplete or redundant summaries, and they frequently ignore associated code snippets, which are essential for accurate defect diagnosis. To address these limitations, we propose a progressive code-integration framework for LLM-based abstractive bug report summarization. Our approach incrementally incorporates long code snippets alongside textual content, overcoming standard LLM context window constraints and producing semantically rich summaries. Evaluated on four benchmark datasets using eight LLMs, our pipeline outperforms extractive baselines by 7.5%-58.2% and achieves performance comparable to state-of-the-art abstractive methods, highlighting the benefits of jointly leveraging textual and code information for enhanced bug comprehension. |
| title | Progressive Code Integration for Abstractive Bug Report Summarization |
| topic | Software Engineering Artificial Intelligence Computation and Language |
| url | https://arxiv.org/abs/2512.00325 |