IntentPrism: Human-AI Intent Manifestation for Web Information Foraging

Zehuan Wang; Jiaqi Xiao; Jingwei Sun; Can Liu

doi:10.1145/3706599.3719744

IntentPrism: Human-AI Intent Manifestation for Web Information Foraging

Zehuan Wang (Co-first Author)
, Jiaqi Xiao (Co-first Author)
, Jingwei Sun
, Can Liu^*

^*Corresponding author for this work

School of Creative Media

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review

4 Citations (Scopus)

Abstract

Intent-based User Interface (IBI) is an emerging topic in HCI about supporting user interaction with intelligent systems. We introduce IntentPrism, an approach to explicitly visualizing LLM-recognized user intents in a web information foraging task, in order to facilitate human-AI collaboration. Implemented as a web browser plug-in, IntentPrism provides real-time intent analysis from bookmarked web content, intent tree visualization and relevant content highlighting on webpages. It aims to support users in refining vague intentions, improving focus, and uncovering relevant content. The preliminary user study (n = 5) showed the promising potential of this approach in refining coarse-grained intents and improving efficiency especially when conducting in-depth exploration tasks. Additionally, user feedback highlights the demands for a multi-layered intent structure and a feedback mechanism for inaccurate highlights. Overall, IntentPrism represents a novel exploration of designing advanced intent-based user interfaces. © 2025 Copyright held by the owner/author(s).

Original language	English
Title of host publication	CHI EA '25
Subtitle of host publication	Proceedings of the Extended Abstracts of the CHI Conference on Human Factors in Computing Systems
Editors	Naomi Yamashita, Vanessa Evers, Koji Yatani, Xianghua (Sharon) Ding
Publisher	Association for Computing Machinery
ISBN (Print)	979-8-4007-1395-8
DOIs	https://doi.org/10.1145/3706599.3719744
Publication status	Published - Apr 2025
Event	2025 ACM CHI Conference on Human Factors in Computing Systems (CHI 2025): IkiCHI - PACIFICO Yokohama, Yokohama, Japan Duration: 26 Apr 2025 → 1 May 2025 https://chi2025.acm.org/

Publication series

Name	Conference on Human Factors in Computing Systems - Proceedings

Conference

Conference	2025 ACM CHI Conference on Human Factors in Computing Systems (CHI 2025)
Abbreviated title	CHI'25
Place	Japan
City	Yokohama
Period	26/04/25 → 1/05/25
Internet address	https://chi2025.acm.org/

Funding

This project is an outcome of the HCI\u00B7X summer research camp 2024. It is partially supported by the National Natural Science Foundation of China (project No. 9240123).

Research Keywords

Information foraging
Intent-based user interfaces
Large language models
User experience

Access Output

10.1145/3706599.3719744

Other Access Options

Check CityUHK Library

Permanent Link

Right click to copy link

Cite this

Wang, Z., Xiao, J., Sun, J., & Liu, C. (2025). IntentPrism: Human-AI Intent Manifestation for Web Information Foraging. In N. Yamashita, V. Evers, K. Yatani, & X. Ding (Eds.), CHI EA '25: Proceedings of the Extended Abstracts of the CHI Conference on Human Factors in Computing Systems Article 345 (Conference on Human Factors in Computing Systems - Proceedings). Association for Computing Machinery. https://doi.org/10.1145/3706599.3719744

Wang, Zehuan ; Xiao, Jiaqi ; Sun, Jingwei et al. / IntentPrism : Human-AI Intent Manifestation for Web Information Foraging. CHI EA '25: Proceedings of the Extended Abstracts of the CHI Conference on Human Factors in Computing Systems. editor / Naomi Yamashita ; Vanessa Evers ; Koji Yatani ; Xianghua (Sharon) Ding. Association for Computing Machinery, 2025. (Conference on Human Factors in Computing Systems - Proceedings).

@inproceedings{ed042814545648fab37b20ec8aba930c,

title = "IntentPrism: Human-AI Intent Manifestation for Web Information Foraging",

abstract = "Intent-based User Interface (IBI) is an emerging topic in HCI about supporting user interaction with intelligent systems. We introduce IntentPrism, an approach to explicitly visualizing LLM-recognized user intents in a web information foraging task, in order to facilitate human-AI collaboration. Implemented as a web browser plug-in, IntentPrism provides real-time intent analysis from bookmarked web content, intent tree visualization and relevant content highlighting on webpages. It aims to support users in refining vague intentions, improving focus, and uncovering relevant content. The preliminary user study (n = 5) showed the promising potential of this approach in refining coarse-grained intents and improving efficiency especially when conducting in-depth exploration tasks. Additionally, user feedback highlights the demands for a multi-layered intent structure and a feedback mechanism for inaccurate highlights. Overall, IntentPrism represents a novel exploration of designing advanced intent-based user interfaces. {\textcopyright} 2025 Copyright held by the owner/author(s).",

keywords = "Information foraging, Intent-based user interfaces, Large language models, User experience",

author = "Zehuan Wang and Jiaqi Xiao and Jingwei Sun and Can Liu",

year = "2025",

month = apr,

doi = "10.1145/3706599.3719744",

language = "English",

isbn = "979-8-4007-1395-8",

series = "Conference on Human Factors in Computing Systems - Proceedings",

publisher = "Association for Computing Machinery",

editor = "Naomi Yamashita and Vanessa Evers and Koji Yatani and Ding, \{Xianghua (Sharon)\}",

booktitle = "CHI EA '25",

address = "United States",

note = "2025 ACM CHI Conference on Human Factors in Computing Systems (CHI 2025) : IkiCHI, CHI'25 ; Conference date: 26-04-2025 Through 01-05-2025",

url = "https://chi2025.acm.org/",

}

Wang, Z, Xiao, J, Sun, J & Liu, C 2025, IntentPrism: Human-AI Intent Manifestation for Web Information Foraging. in N Yamashita, V Evers, K Yatani & X Ding (eds), CHI EA '25: Proceedings of the Extended Abstracts of the CHI Conference on Human Factors in Computing Systems., 345, Conference on Human Factors in Computing Systems - Proceedings, Association for Computing Machinery, 2025 ACM CHI Conference on Human Factors in Computing Systems (CHI 2025), Yokohama, Japan, 26/04/25. https://doi.org/10.1145/3706599.3719744

IntentPrism: Human-AI Intent Manifestation for Web Information Foraging. / Wang, Zehuan (Co-first Author); Xiao, Jiaqi (Co-first Author); Sun, Jingwei et al.
CHI EA '25: Proceedings of the Extended Abstracts of the CHI Conference on Human Factors in Computing Systems. ed. / Naomi Yamashita; Vanessa Evers; Koji Yatani; Xianghua (Sharon) Ding. Association for Computing Machinery, 2025. 345 (Conference on Human Factors in Computing Systems - Proceedings).

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review

TY - GEN

T1 - IntentPrism

T2 - 2025 ACM CHI Conference on Human Factors in Computing Systems (CHI 2025)

AU - Wang, Zehuan

AU - Xiao, Jiaqi

AU - Sun, Jingwei

AU - Liu, Can

PY - 2025/4

Y1 - 2025/4

N2 - Intent-based User Interface (IBI) is an emerging topic in HCI about supporting user interaction with intelligent systems. We introduce IntentPrism, an approach to explicitly visualizing LLM-recognized user intents in a web information foraging task, in order to facilitate human-AI collaboration. Implemented as a web browser plug-in, IntentPrism provides real-time intent analysis from bookmarked web content, intent tree visualization and relevant content highlighting on webpages. It aims to support users in refining vague intentions, improving focus, and uncovering relevant content. The preliminary user study (n = 5) showed the promising potential of this approach in refining coarse-grained intents and improving efficiency especially when conducting in-depth exploration tasks. Additionally, user feedback highlights the demands for a multi-layered intent structure and a feedback mechanism for inaccurate highlights. Overall, IntentPrism represents a novel exploration of designing advanced intent-based user interfaces. © 2025 Copyright held by the owner/author(s).

AB - Intent-based User Interface (IBI) is an emerging topic in HCI about supporting user interaction with intelligent systems. We introduce IntentPrism, an approach to explicitly visualizing LLM-recognized user intents in a web information foraging task, in order to facilitate human-AI collaboration. Implemented as a web browser plug-in, IntentPrism provides real-time intent analysis from bookmarked web content, intent tree visualization and relevant content highlighting on webpages. It aims to support users in refining vague intentions, improving focus, and uncovering relevant content. The preliminary user study (n = 5) showed the promising potential of this approach in refining coarse-grained intents and improving efficiency especially when conducting in-depth exploration tasks. Additionally, user feedback highlights the demands for a multi-layered intent structure and a feedback mechanism for inaccurate highlights. Overall, IntentPrism represents a novel exploration of designing advanced intent-based user interfaces. © 2025 Copyright held by the owner/author(s).

KW - Information foraging

KW - Intent-based user interfaces

KW - Large language models

KW - User experience

UR - https://www.scopus.com/pages/publications/105005755934

UR - https://www.scopus.com/record/pubmetrics.uri?eid=2-s2.0-105005755934&origin=recordpage

U2 - 10.1145/3706599.3719744

DO - 10.1145/3706599.3719744

M3 - RGC 32 - Refereed conference paper (with host publication)

SN - 979-8-4007-1395-8

T3 - Conference on Human Factors in Computing Systems - Proceedings

BT - CHI EA '25

A2 - Yamashita, Naomi

A2 - Evers, Vanessa

A2 - Yatani, Koji

A2 - Ding, Xianghua (Sharon)

PB - Association for Computing Machinery

Y2 - 26 April 2025 through 1 May 2025

ER -

Wang Z, Xiao J, Sun J, Liu C. IntentPrism: Human-AI Intent Manifestation for Web Information Foraging. In Yamashita N, Evers V, Yatani K, Ding X, editors, CHI EA '25: Proceedings of the Extended Abstracts of the CHI Conference on Human Factors in Computing Systems. Association for Computing Machinery. 2025. 345. (Conference on Human Factors in Computing Systems - Proceedings). Epub 2025 Apr 25. doi: 10.1145/3706599.3719744

IntentPrism: Human-AI Intent Manifestation for Web Information Foraging

Abstract

Publication series

Conference

Funding

Research Keywords

Access Output

Other Access Options

Permanent Link

Other Files and Links

Fingerprint

Cite this