Characterizing Multi-Hunk Patches: Divergence, Proximity, and LLM Repair Challenges
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_ | 1866912715346280448 |
|---|---|
| author | Nashid, Noor Ding, Daniel Gallaba, Keheliya Hassan, Ahmed E. Mesbah, Ali |
| author_facet | Nashid, Noor Ding, Daniel Gallaba, Keheliya Hassan, Ahmed E. Mesbah, Ali |
| contents | Multi-hunk bugs, where fixes span disjoint regions of code, are common in practice, yet remain underrepresented in automated repair. Existing techniques and benchmarks pre-dominantly target single-hunk scenarios, overlooking the added complexity of coordinating semantically related changes across the codebase. In this work, we characterize HUNK4J, a dataset of multi-hunk patches derived from 372 real-world defects. We propose hunk divergence, a metric that quantifies the variation among edits in a patch by capturing lexical, structural, and file-level differences, while incorporating the number of hunks involved. We further define spatial proximity, a classification that models how hunks are spatially distributed across the program hierarchy. Our empirical study spanning six LLMs reveals that model success rates decline with increased divergence and spatial dispersion. Notably, when using the LLM alone, no model succeeds in the most dispersed Fragment class. These findings highlight a critical gap in LLM capabilities and motivate divergence-aware repair strategies. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_04418 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Characterizing Multi-Hunk Patches: Divergence, Proximity, and LLM Repair Challenges Nashid, Noor Ding, Daniel Gallaba, Keheliya Hassan, Ahmed E. Mesbah, Ali Software Engineering Multi-hunk bugs, where fixes span disjoint regions of code, are common in practice, yet remain underrepresented in automated repair. Existing techniques and benchmarks pre-dominantly target single-hunk scenarios, overlooking the added complexity of coordinating semantically related changes across the codebase. In this work, we characterize HUNK4J, a dataset of multi-hunk patches derived from 372 real-world defects. We propose hunk divergence, a metric that quantifies the variation among edits in a patch by capturing lexical, structural, and file-level differences, while incorporating the number of hunks involved. We further define spatial proximity, a classification that models how hunks are spatially distributed across the program hierarchy. Our empirical study spanning six LLMs reveals that model success rates decline with increased divergence and spatial dispersion. Notably, when using the LLM alone, no model succeeds in the most dispersed Fragment class. These findings highlight a critical gap in LLM capabilities and motivate divergence-aware repair strategies. |
| title | Characterizing Multi-Hunk Patches: Divergence, Proximity, and LLM Repair Challenges |
| topic | Software Engineering |
| url | https://arxiv.org/abs/2506.04418 |