The paper investigates the problem of over‑editing by large language models when repairing code, showing that even state‑of‑the‑art models like GPT‑5.5 frequently rewrite more code than necessary. Using a benchmark of 400 BigCodeBench problems with controlled AST corruptions, the authors quantify excess edits and demonstrate that a simple preservation instruction can reduce unnecessary changes and improve pass rates. They further explore training strategies, finding that reinforcement learning yields the best balance between edit fidelity and performance retention, highlighting edit fidelity as a distinct, measurable dimension of code‑repair quality.
By Tongyao Zhu, Wei Hern Lim, Min-Yen Kan
The paper compares two output regimes for code-editing language models: direct generation, where the model outputs the entire modified file, and iterative diff-based generation, where the model emits a sequence of localized edits. Experiments on Flutter/Dart tasks show that direct generation consistently outperforms diff-based generation across metrics such as compilation success, token efficiency, and quality judgments. However, diff-based generation can be competitive for short, spatially localized edits, particularly in refactoring and error-handling tasks with few edit steps.
By Andrej Andrejev
The paper introduces the Harmful Memorization Index (HMI) to measure when large language models (LLMs) fail to adapt to small semantic changes in coding tasks, producing code that is superficially similar to the original solution. It proposes an automated code‑rewriting pipeline that generates semantically different variants of tasks by altering core logic elements, and uses HMI to combine similarity metrics with performance degradation. Experiments on MBPP+ and BigCodeBench show that HMI does not simply grow with model size, is higher for certain logic‑edit types, and that supervised fine‑tuning can increase HMI while PPO offers a better accuracy–HMI trade‑off.
By Lizhe Zhang, Wentao Chen, Li Zhong, Letian Peng, Zilong Wang, Jingbo Shang
The paper introduces DECODE, a dataset of 53.6K real‑world in‑IDE edits of AI‑generated code from over 1,000 developers, and uses it to study when, why, and how developers modify such code. Findings show developers spend little effort editing and often abandon AI outputs, highlighting the need for LLMs to infer intent from edits. Experiments reveal that while frontier models can generate edits that align with developer intent, they tend to over‑edit and revert changes; fine‑tuning improves performance but does not fully close the gap.
By Jenny T. Liang, Mihika Bairathi, Wayne Chi, Ameet Talwalkar, Nishant Subramani, Valerie Chen
The paper investigates the problem of over‑editing by large language models (LLMs) when repairing code, showing that even state‑of‑the‑art models like GPT‑5.5 often rewrite more code than necessary. Using a benchmark of 400 BigCodeBench problems with controlled AST‑level corruptions, the authors quantify over‑editing and demonstrate that a simple preservation instruction can significantly reduce excess edits and cognitive complexity while improving Pass@1. They further explore post‑training strategies, finding that reinforcement learning yields the best balance between edit fidelity and performance retention, thereby establishing edit fidelity as a distinct, measurable dimension of code‑repair quality.
arXiv:2511. 05852v4 Announce Type: replace-cross Abstract: Knowledge editing (KE) offers a lightweight alternative to retraining for updating large language models (LLMs).
By Yinjie Cheng, Paul Youssef, Christin Seifert, J\"org Schl\"otterer, Zhixue Zhao