| title | When Models Edit Too Much: On the Fidelity of Minimal Code Edits |
|---|---|
| authors | Tongyao Zhu, Wei Hern Lim, Min-Yen Kan |
| date | 2026-09-03 |
| venue | arXiv (preprint, not peer reviewed) |
| id | arXiv:2609.04061 |
| affiliation | National University of Singapore |
| upvotes | 8 (Hugging Face Daily Papers, 2026-11-01) |
| links | abs pdf hf code |
| abstract | Large language models (LLMs) are increasingly used to edit existing code, but correctness alone is not enough: useful repairs should also be minimal, reviewable, and faithful to the original implementation. We study over-editing, the tendency of a model to rewrite code beyond what is required to fix a bug. We construct an evaluation framework from 400 BigCodeBench problems by injecting controlled AST-level corruptions into reference solutions, giving each repair task a known minimal patch. Across frontier LLMs, over-editing is widespread even among strong models like GPT-5.5: high Pass@1 can coexist with unnecessarily large edits and added cognitive complexity. A preservation instruction substantially reduces this behavior, lowering average excess Levenshtein distance from 0.195 to 0.131, reducing added cognitive complexity by 26.6%, and increasing Pass@1 by 2.3 points. However, these gains do not simply follow from a larger reasoning budget or larger models. We next ask whether minimal editing can be learned directly during post-training. We observe that supervised fine-tuning overfits to seen corruption patterns, whereas reinforcement learning gives the best out-of-domain edit-fidelity and performance-retention trade-off. These results position edit fidelity as a distinct axis of code-repair quality and show that it can be measured and learned. |
cite
@misc{zhu2026when,
title={When Models Edit Too Much: On the Fidelity of Minimal Code Edits},
author={Tongyao Zhu and Wei Hern Lim and Min-Yen Kan},
year={2026},
eprint={2609.04061},
archivePrefix={arXiv},
url={https://arxiv.org/abs/2609.04061}
}