Direkt zum Inhalt

Bink, Markus ; Risius, Marten ; Elsweiler, David ; Kruschwitz, Udo

"Can You Tell Me?": Designing Copilots to Support Human Judgement in Online Information Seeking

Conference or workshop item

Bink, Markus, Risius, Marten, Elsweiler, David and Kruschwitz, Udo (2026) "Can You Tell Me?": Designing Copilots to Support Human Judgement in Online Information Seeking. In: CHIIR '26: 2026 ACM SIGIR Conference on Human Information Interaction and Retrieval, March 22 - 26, 2026, Seattle, USA.

DOI to cite this document: 10.5283/epub.80847


Abstract

Generative AI (GenAI) tools are transforming information seeking, but their fluent, authoritative responses risk overreliance and discourage independent verification and reasoning. Rather than replacing the cognitive work of users, GenAI systems should be designed to support and scaffold it. Therefore, this paper introduces an LLM-based conversational copilot designed to scaffold information ...

Generative AI (GenAI) tools are transforming information seeking, but their fluent, authoritative responses risk overreliance and discourage independent verification and reasoning. Rather than replacing the cognitive work of users, GenAI systems should be designed to support and scaffold it. Therefore, this paper introduces an LLM-based conversational copilot designed to scaffold information evaluation rather than provide answers and foster digital literacy skills. In a pre-registered, randomised controlled trial (N=261) examining three interface conditions including a chat-based copilot, our mixed-methods analysis reveals that users engaged deeply with the copilot, demonstrating metacognitive reflection. However, the copilot did not significantly improve answer correctness or search engagement, largely due to a "time-on-chat vs. exploration" trade-off and users’ bias toward positive information. Qualitative findings reveal tension between the copilot’s Socratic approach and users’ desire for efficiency. These results highlight both the promise and pitfalls of pedagogical copilots, and we outline design pathways to reconcile literacy goals with efficiency demands.



Involved Institutions


Details

Item typeConference or workshop item (Paper)
Title of BookProceedings of the 2026 Conference on Human Information Interaction and Retrieval
Open Access TypeAssoc. of Comp. Machinery (ACM)
Page Rangepp. 172-182
Date2026
Date of publication30 Sep 2026 10:40
InstitutionsLanguages and Literatures > Institut für Information und Medien, Sprache und Kultur (I:IMSK) > Lehrstuhl für Informationswissenschaft (Prof. Dr. Udo Kruschwitz)
Informatics and Data Science > Department Human-Centered Computing > Lehrstuhl für Informationswissenschaft (Prof. Dr. Udo Kruschwitz)
Identification Number
ValueType
10.1145/3786304.3787866DOI
Keywordssearch behaviour, copilot, misinformation, boosting, mixed-methods, learning to search, ai overview
Dewey Decimal Classification000 Computer science, information & general works > 004 Computer science
StatusPublished
RefereedYes, this version has been refereed
Created at the University of RegensburgPartially
URN of the UB Regensburgurn:nbn:de:bvb:355-epub-808472
Item ID80847

Export bibliographical data

Owner only: item control page

nach oben