EyeMulator: Improving Code Language Models by Mimicking Human Visual Attention

arXiv:2508.16771v2 Announce Type: replace-cross Abstract: Code Language Models (CodeLLMs) traditionally learn attention based solely on statistical input-output token correlations ("machine attention"). In contrast, human developers rely on intuition, selectively fixating on semantically salient tokens during program comprehension. We present EyeMulator, a model-agnostic technique to align CodeLLM attention with human visual attention without architectural changes. By extracting scan paths from