GazeSummary: Exploring Gaze as an Implicit Prompt for Personalization in Text-based LLM Tasks

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Ding, Jiexin, Zhang, Yizhuo, Liu, Xinyun, chen, Ke, Wang, Yuntao, Patel, Shwetak, Gadre, Akshay
Formato: Preprint
Publicado: 2026
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866914277845106688
author Ding, Jiexin
Zhang, Yizhuo
Liu, Xinyun
chen, Ke
Wang, Yuntao
Patel, Shwetak
Gadre, Akshay
author_facet Ding, Jiexin
Zhang, Yizhuo
Liu, Xinyun
chen, Ke
Wang, Yuntao
Patel, Shwetak
Gadre, Akshay
contents Smart glasses are accelerating progress toward more seamless and personalized LLM-based assistance by integrating multimodal inputs. Yet, these inputs rely on obtrusive explicit prompts. The advent of gaze tracking on smart devices offers a unique opportunity to extract implicit user intent for personalization. This paper investigates whether LLMs can interpret user gaze for text-based tasks. We evaluate different gaze representations for personalization and validate their effectiveness in realistic reading tasks. Results show that LLMs can leverage gaze to generate high-quality personalized summaries and support users in downstream tasks, highlighting the feasibility and value of gaze-driven personalization for future mobile and wearable LLM applications.
format Preprint
id arxiv_https___arxiv_org_abs_2601_17676
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle GazeSummary: Exploring Gaze as an Implicit Prompt for Personalization in Text-based LLM Tasks
Ding, Jiexin
Zhang, Yizhuo
Liu, Xinyun
chen, Ke
Wang, Yuntao
Patel, Shwetak
Gadre, Akshay
Human-Computer Interaction
Smart glasses are accelerating progress toward more seamless and personalized LLM-based assistance by integrating multimodal inputs. Yet, these inputs rely on obtrusive explicit prompts. The advent of gaze tracking on smart devices offers a unique opportunity to extract implicit user intent for personalization. This paper investigates whether LLMs can interpret user gaze for text-based tasks. We evaluate different gaze representations for personalization and validate their effectiveness in realistic reading tasks. Results show that LLMs can leverage gaze to generate high-quality personalized summaries and support users in downstream tasks, highlighting the feasibility and value of gaze-driven personalization for future mobile and wearable LLM applications.
title GazeSummary: Exploring Gaze as an Implicit Prompt for Personalization in Text-based LLM Tasks
topic Human-Computer Interaction
url https://arxiv.org/abs/2601.17676