cs.LGNov 10, 2026

Leveraging Psychophysical Attentional Distribution for Gaze-Augmented Reward Modeling

Authors: Chaeho Lee, Junyup Kim, Wansoo Kim, Young Min Jung, Sang Ho Lee

Organizations: School of Digital Humanities and Computational Social Sciences, KAIST · Department of Brain & Cognitive Sciences, KAIST · Graduate School of Data Science, KAIST

Abstract

Integrating human feedback into language models has gained increasing attention as a means to align model outputs with human preferences, with Reinforcement Learning from Human Feedback (RLHF) serving as a prominent framework for preference-based alignment. Recent studies have incorporated eye-tracking (ET) data as an additional supervisory signal for reward model training, grounding reward learning in human reading behavior. Building on this approach, we extend prior fixation-centric models by leveraging established findings from cognitive psychology on human letter recognition. Specifically, we model visual attention as a spatially graded distribution centered on the current gaze location and incorporate this representation into reward model training. Our results show that the reward model trained with the proposed gaze distribution achieves higher preference prediction accuracy than a baseline model. Moreover, some results from our experiments are qualitatively consistent with established findings on human attention during reading, suggesting that they potentially capture cognitively meaningful aspects of human attention allocation.

Figures & tables

Appendix figures & tables2 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Attention Limited Reward Learning

    Jul 6, 2026Wenqian XingPairwise Preference LearningReward Modeling

  2. Comparing Human Gaze and Vision-Language Model Attention in Safety-Relevant Environments

    Jun 13, 2026Marta Vallejo, Siwen WangVLM EvaluationLarge Vision-Language Models

  3. Eyettention II: A Dual-Sequence Architecture for Modeling Fixation Location, Within-Word Landing Position, and Fixation Duration in Reading

    Jun 1, 2026Shuwen Deng, Cui Ding, David R. Reich +2Eye TrackingComputational Psycholinguistics