Guardado en:
Detalles Bibliográficos
Autores principales: Siyan, Li, Zhang, Jason, Maharaj, Akash, Shi, Yuanming, Li, Yunyao
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:https://arxiv.org/abs/2511.23376
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866912736341917696
author Siyan, Li
Zhang, Jason
Maharaj, Akash
Shi, Yuanming
Li, Yunyao
author_facet Siyan, Li
Zhang, Jason
Maharaj, Akash
Shi, Yuanming
Li, Yunyao
contents Novice and expert users have different systematic preferences in task-oriented dialogues. However, whether catering to these preferences actually improves user experience and task performance remains understudied. To investigate the effects of expertise-based personalization, we first built a version of an enterprise AI assistant with passive personalization. We then conducted a user study where participants completed timed exams, aided by the two versions of the AI assistant. Preliminary results indicate that passive personalization helps reduce task load and improve assistant perception, but reveal task-specific limitations that can be addressed through providing more user agency. These findings underscore the importance of combining active and passive personalization to optimize user experience and effectiveness in enterprise task-oriented environments.
format Preprint
id arxiv_https___arxiv_org_abs_2511_23376
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Is Passive Expertise-Based Personalization Enough? A Case Study in AI-Assisted Test-Taking
Siyan, Li
Zhang, Jason
Maharaj, Akash
Shi, Yuanming
Li, Yunyao
Human-Computer Interaction
Computation and Language
Novice and expert users have different systematic preferences in task-oriented dialogues. However, whether catering to these preferences actually improves user experience and task performance remains understudied. To investigate the effects of expertise-based personalization, we first built a version of an enterprise AI assistant with passive personalization. We then conducted a user study where participants completed timed exams, aided by the two versions of the AI assistant. Preliminary results indicate that passive personalization helps reduce task load and improve assistant perception, but reveal task-specific limitations that can be addressed through providing more user agency. These findings underscore the importance of combining active and passive personalization to optimize user experience and effectiveness in enterprise task-oriented environments.
title Is Passive Expertise-Based Personalization Enough? A Case Study in AI-Assisted Test-Taking
topic Human-Computer Interaction
Computation and Language
url https://arxiv.org/abs/2511.23376