Obey, Diverge, Collapse: Blind Obedience to Incorrect Instructions Drives Code LLMs to Irrecoverable Code Semantic Collapse
Code language models are now trusted collaborators in production workflows for debugging, refactoring, and iterative repair, and every benchmark that evaluates them assumes the instructions they act on are correct. We study what happens when that assumption breaks. We evaluate code language models across four experiments designed to assess whether models resist or obey incorrect instructions in single-pass and iterative repair settings, using the RunBugRun dataset of algorithmic Python problems with deterministic test cases. Our findings reveal a striking behavioral pattern: models correctly identify an incorrect instruction as wrong, then follow it anyway. This compliance unknowingly int...
| Authors | Raj Jaiswal, Anany Singh Divy, Savar Bhasin et al. |
|---|---|
| Primary category | cs.SE |
| Published | 5 July 2026 |
| Last updated at source | 5 July 2026 |
Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 17 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.