Reinforcement Learning from Human Feedback (RLHF) aligns language models with human preferences but is computationally expensive. We explore two approaches that leverage human gaze modeling to enhance RLHF: (1) gaze-aware reward models and (2) gaze-based distribution of sparse rewards at token level. Our experiments demonstate that gaze-informed RLHF achieves faster convergence while maintaining or slightly improving performance, thus, reducing computational costs during policy optimization. These results show that human gaze provides a valuable and underused signal for policy optimization, pointing to a promising direction for improving RLHF efficiency.
@article{arxiv.2507.09016,
title = {Enhancing RLHF with Human Gaze Modeling},
author = {Karim Galliamov and Ivan Titov and Ilya Pershin},
journal= {arXiv preprint arXiv:2507.09016},
year = {2025}
}