Saved in:
Bibliographic Details
Main Authors: Galliamov, Karim, Titov, Ivan, Pershin, Ilya
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2507.09016
Tags: Add Tag
No Tags, Be the first to tag this record!
Table of Contents:
  • 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.