Megadose AI progress, ranked and analyzed.

To Add Is Machine, To Delete Is Human: Measuring and Mitigating Deletion Avoidance in LLM Code Editing

· HF Daily Papers ·
LLM code patches often avoid deleting the code they are supposed to remove, even when the fix passes tests.

The paper measures this “deletion avoidance” across leading SWE-bench Verified models, finding they usually reach the right file but cut the exact required line less than 52% of the time. In 29.0% of passing patches, models instead wrap targeted code in guards or fallbacks. When the authors added tests that fail if the old code remains, four frontier models dropped from 63.2% to 41.9%. A deletion-only benchmark still left the best model failing one in five tasks, though post-training on deletion reduced the behavior. HF Daily Papers' note

score 6

Categories: Research