Preprint
Sep 2026
Identity or Prompt Noise? A Calibrated Invariance Audit of LLM Code Generation
Identity cues are irrelevant to a fixed programming specification, but raw counterfactual differences can arise from unequal samples and prompt wording. We audit 30.73 million executed Python generations from seven checkpoints on HumanEval+ and MBPP+, supplemented by an exploratory 550B slice, under model-assigned gend...
M. Eren, Ryan C. Barron, E. Michalak et al.
· 0 citations