Steering AI-driven Personalization of Scientific Text for General Audiences
Proceedings of the ACM on Human-Computer Interaction · 18.10.2025 · 9 (7) · 1-28
DOI: 10.1145/3757660 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the ACM on Human-Computer Interaction, online erschienen am 16.10.2025. Verfasst von Taewook Kim und 3 weiteren Autor:innen. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 100 Literaturangaben.
Abstract (Originalsprache)
Digital media platforms (e.g., science blogs) offer opportunities to communicate scientific content to general audiences at scale. However, these audiences vary in their scientific expertise, literacy levels, and personal backgrounds, making effective science communication challenging. To address this challenge, we designed TranSlider, an AI-powered tool that generates personalized translations of scientific text based on individual user profiles (e.g., hobbies, location, and education). Our tool features an interactive slider that allows users to steer the degree of personalization from 0 (weakly relatable) to 100 (strongly relatable), leveraging LLMs to generate the translations with chosen degrees. Through an exploratory study with 15 participants, we investigated both the utility of these AI-personalized translations and how interactive reading features influenced users' understanding and reading experiences. We found that participants who preferred higher degrees of personalization appreciated the relatable and contextual translations, while those who preferred lower degrees valued concise translations with subtle contextualization. Furthermore, participants reported the compounding effect of multiple translations on their understanding of scientific content. Drawing on these findings, we discuss several implications for facilitating science communication and designing steerable interfaces to support human-AI alignment.
Zitieren
APA
Kim, T., Agarwal, D., Ackerman, J., & Saha, M. (2025). Steering AI-driven Personalization of Scientific Text for General Audiences. Proceedings of the ACM on Human-Computer Interaction, 9(7), 1-28. https://doi.org/10.1145/3757660
Vancouver
Kim T, Agarwal D, Ackerman J, Saha M. Steering AI-driven Personalization of Scientific Text for General Audiences. Proceedings of the ACM on Human-Computer Interaction. 2025;9(7):1-28. doi:10.1145/3757660
BibTeX
@article{Kim2025,
author = {Kim, Taewook and Agarwal, Dhruv and Ackerman, Jordan and Saha, Manaswi},
title = {Steering AI-driven Personalization of Scientific Text for General Audiences},
journal = {Proceedings of the ACM on Human-Computer Interaction},
year = {2025},
volume = {9},
number = {7},
pages = {1--28},
doi = {10.1145/3757660}
}
EUVIMED