Skip to main content
Search

Chaeho Lee

1 related articles

Subscribe to updates
  1. arXiv

    Gaze no longer stops at the fixated word: spreading reading time into an asymmetric attention profile lifts preference accuracy by up to 13.02%

    In reward-model training, eye-tracking data previously attached only to the directly fixated token, ignoring that readers take in text around the fixation. The new step spreads each token's predicted total reading time onto neighboring tokens with a learnable asymmetric Gaussian kernel before the gaze features reach the existing projector and reward model. On OASST1, accuracy rose from 68.38% to 74.73% for Llama-3-8B-Instruct under GazeConcat and from 69.23% to 74.81% for Llama-3-8B; on UltraFeedback it rose from 65.65% to 74.20%.

You’re all caught up