{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,17]],"date-time":"2025-10-17T02:11:23Z","timestamp":1760667083942,"version":"build-2065373602"},"reference-count":100,"publisher":"Association for Computing Machinery (ACM)","issue":"7","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["Proc. ACM Hum.-Comput. Interact."],"published-print":{"date-parts":[[2025,10,18]]},"abstract":"<jats:p>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.<\/jats:p>","DOI":"10.1145\/3757660","type":"journal-article","created":{"date-parts":[[2025,10,16]],"date-time":"2025-10-16T17:06:01Z","timestamp":1760634361000},"page":"1-28","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Steering AI-driven Personalization of Scientific Text for General Audiences"],"prefix":"10.1145","volume":"9","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4796-300X","authenticated-orcid":false,"given":"Taewook","family":"Kim","sequence":"first","affiliation":[{"name":"Northwestern University, Evanston, IL, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1090-3583","authenticated-orcid":false,"given":"Dhruv","family":"Agarwal","sequence":"additional","affiliation":[{"name":"Cornell University, Ithaca, NY, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-8309-4550","authenticated-orcid":false,"given":"Jordan","family":"Ackerman","sequence":"additional","affiliation":[{"name":"Accenture Center for Advanced AI, Mountain View, CA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2981-9370","authenticated-orcid":false,"given":"Manaswi","family":"Saha","sequence":"additional","affiliation":[{"name":"Accenture Labs, San Francisco, CA, USA"}]}],"member":"320","published-online":{"date-parts":[[2025,10,16]]},"reference":[{"key":"e_1_2_2_1_1","unstructured":"2025. DeviantArt. https:\/\/www.deviantart.com\/"},{"key":"e_1_2_2_2_1","unstructured":"2025. Google Scholar. https:\/\/scholar.google.com\/"},{"key":"e_1_2_2_3_1","unstructured":"2025. Midjourney. https:\/\/www.midjourney.com\/home"},{"key":"e_1_2_2_4_1","unstructured":"2025. Semantic Scholar. https:\/\/www.semanticscholar.org\/"},{"key":"e_1_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/3025453.3025631"},{"key":"e_1_2_2_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/1278366.1278367"},{"key":"e_1_2_2_7_1","unstructured":"Anthropic. 2024. Claude 3.5 Sonnet. https:\/\/claude.ai\/"},{"key":"e_1_2_2_8_1","unstructured":"Akari Asai Jacqueline He* Rulin Shao* Weijia Shi Amanpreet Singh Joseph Chee Chang Kyle Lo Luca Soldaini Sergey Feldman Tian D'arcy Mike David Wadden Matt Latzke Minyang Pan Ji Shengyan Liu Hao Tong Bohao Wu Yanyu Xiong Luke Zettlemoyer Dan Weld Graham Neubig Doug Downey Wen-tau Yih Pang Wei Koh and Hannaneh Hajishirzi. 2024. OpenScholar: Synthesizing Scientific Literature with Retrieval-Augmented Language Models. Arxiv (2024)."},{"key":"e_1_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.429"},{"key":"e_1_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/3613904.3642289"},{"key":"e_1_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/3589955"},{"key":"e_1_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/3708359.3712110"},{"key":"e_1_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.1177\/1075547007311971"},{"key":"e_1_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.1002\/tea.21186"},{"key":"e_1_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/3491102.3502028"},{"key":"e_1_2_2_16_1","doi-asserted-by":"publisher","unstructured":"Sid Black Leo Gao Phil Wang Connor Leahy and Stella Biderman. 2021. GPT-Neo: Large Scale Autoregressive Language Modeling with Mesh-Tensorflow. doi:10.5281\/zenodo.5297715 If you use this software please cite it using these metadata.","DOI":"10.5281\/zenodo.5297715"},{"key":"e_1_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.1191\/1478088706qp063oa"},{"key":"e_1_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.1186\/s43031-022-00051-4"},{"key":"e_1_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.22323\/2.19030202"},{"key":"e_1_2_2_20_1","unstructured":"M. Bucchi and B. Trench. 2014. Routledge Handbook of Public Communication of Science and Technology: Second edition. Taylor & Francis. https:\/\/books.google.com\/books?id=KrLcAwAAQBAJ"},{"key":"e_1_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3449287"},{"key":"e_1_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.1177\/09636625030122004"},{"key":"e_1_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3654777.3676352"},{"key":"e_1_2_2_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/2998181.2998240"},{"key":"e_1_2_2_25_1","doi-asserted-by":"publisher","DOI":"10.2519\/jospt.2018.0601"},{"key":"e_1_2_2_26_1","doi-asserted-by":"publisher","DOI":"10.2753\/MER1052-8008240206"},{"key":"e_1_2_2_27_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-acl.243"},{"key":"e_1_2_2_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/2556288.2557214"},{"key":"e_1_2_2_29_1","first-page":"195","volume-title":"AMIA Annual Symposium Proceedings 2006","author":"Dimarco C","year":"2006","unstructured":"C Dimarco, P Bray, HD Covvey, DD Cowan, V Diciccio, E Hovy, Joan Lipa, and C Yang. 2006. Authoring and generation of individualized patient education materials. AMIA Annual Symposium Proceedings 2006 (2006), 195-199."},{"key":"e_1_2_2_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/3591196.3593516"},{"key":"e_1_2_2_31_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.421"},{"key":"e_1_2_2_32_1","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1213273110"},{"key":"e_1_2_2_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581641.3584034"},{"key":"e_1_2_2_34_1","doi-asserted-by":"publisher","DOI":"10.1177\/1745691614551642"},{"key":"e_1_2_2_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/3479566"},{"key":"e_1_2_2_36_1","doi-asserted-by":"publisher","DOI":"10.4148\/1051-0834.1882"},{"key":"e_1_2_2_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/3613904.3642699"},{"key":"e_1_2_2_38_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-024-49753-5"},{"key":"e_1_2_2_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/3613905.3650851"},{"key":"e_1_2_2_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/3411764.3445648"},{"key":"e_1_2_2_41_1","doi-asserted-by":"publisher","DOI":"10.5210\/fm.v22i10.8065"},{"key":"e_1_2_2_42_1","unstructured":"Chris Hogan. 2024. Science Daily. https:\/\/www.sciencedaily.com\/"},{"key":"e_1_2_2_43_1","doi-asserted-by":"publisher","DOI":"10.1145\/3134688"},{"key":"e_1_2_2_44_1","doi-asserted-by":"publisher","DOI":"10.1145\/3173574.3173608"},{"key":"e_1_2_2_45_1","doi-asserted-by":"publisher","DOI":"10.1145\/2531602.2531645"},{"key":"e_1_2_2_46_1","doi-asserted-by":"publisher","DOI":"10.1177\/1077699016685558"},{"key":"e_1_2_2_47_1","doi-asserted-by":"publisher","DOI":"10.1145\/3610080"},{"key":"e_1_2_2_48_1","doi-asserted-by":"publisher","DOI":"10.1145\/3290605.3300383"},{"key":"e_1_2_2_49_1","doi-asserted-by":"publisher","DOI":"10.1145\/3613904.3642573"},{"key":"e_1_2_2_50_1","doi-asserted-by":"publisher","DOI":"10.1145\/3613904.3642529"},{"key":"e_1_2_2_51_1","doi-asserted-by":"publisher","DOI":"10.1145\/3359181"},{"key":"e_1_2_2_52_1","doi-asserted-by":"publisher","DOI":"10.1145\/3491102.3502053"},{"key":"e_1_2_2_53_1","volume-title":"DeScipher: A Text Simplification Tool for Science Journalism. In ComputationJournalism Symposium.","author":"Kim Yea-Seul","year":"2015","unstructured":"Yea-Seul Kim, Jessica Hullman, and Eytan Adar. 2015. DeScipher: A Text Simplification Tool for Science Journalism. In ComputationJournalism Symposium."},{"key":"e_1_2_2_54_1","doi-asserted-by":"publisher","DOI":"10.1145\/2858036.2858440"},{"key":"e_1_2_2_55_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cell.2024.03.006"},{"key":"e_1_2_2_56_1","doi-asserted-by":"publisher","DOI":"10.1145\/2675133.2675166"},{"key":"e_1_2_2_57_1","doi-asserted-by":"publisher","DOI":"10.1145\/3654777.3676419"},{"key":"e_1_2_2_58_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i11.21557"},{"key":"e_1_2_2_59_1","doi-asserted-by":"publisher","DOI":"10.5194\/gc-7-201-2024"},{"key":"e_1_2_2_60_1","doi-asserted-by":"publisher","DOI":"10.1145\/3610038"},{"key":"e_1_2_2_61_1","doi-asserted-by":"publisher","DOI":"10.1145\/3432915"},{"key":"e_1_2_2_62_1","doi-asserted-by":"publisher","DOI":"10.3390\/nu16071005"},{"key":"e_1_2_2_63_1","doi-asserted-by":"publisher","DOI":"10.4093\/dmj.2011.35.1.50"},{"key":"e_1_2_2_64_1","doi-asserted-by":"publisher","DOI":"10.1145\/3706598.3714262"},{"key":"e_1_2_2_65_1","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0224262"},{"key":"e_1_2_2_66_1","doi-asserted-by":"publisher","DOI":"10.1145\/3476034"},{"key":"e_1_2_2_67_1","doi-asserted-by":"publisher","DOI":"10.1080\/23299460.2018.1434739"},{"key":"e_1_2_2_68_1","doi-asserted-by":"publisher","DOI":"10.1145\/3361118"},{"key":"e_1_2_2_69_1","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0241972"},{"key":"e_1_2_2_70_1","doi-asserted-by":"publisher","DOI":"10.1523\/JNEUROSCI.0086-16.2016"},{"key":"e_1_2_2_71_1","unstructured":"Meta. 2024. Meta Llama 3. https:\/\/llama.meta.com\/"},{"key":"e_1_2_2_72_1","doi-asserted-by":"publisher","DOI":"10.1145\/3706598.3714164"},{"key":"e_1_2_2_73_1","doi-asserted-by":"publisher","DOI":"10.1111\/ajps.12357"},{"key":"e_1_2_2_74_1","doi-asserted-by":"publisher","DOI":"10.1145\/3657604.3662033"},{"key":"e_1_2_2_75_1","doi-asserted-by":"publisher","DOI":"10.1145\/3637348"},{"key":"e_1_2_2_76_1","unstructured":"OpenAI. 2022. ChatGPT. https:\/\/openai.com\/chatgpt\/"},{"key":"e_1_2_2_77_1","unstructured":"G. Orwell. 2024. 1984. Modernista. https:\/\/books.google.com\/books?id=ET0EEQAAQBAJ"},{"key":"e_1_2_2_78_1","unstructured":"Long Ouyang Jeff Wu Xu Jiang Diogo Almeida Carroll L. Wainwright Pamela Mishkin Chong Zhang Sandhini Agarwal Katarina Slama Alex Ray John Schulman Jacob Hilton Fraser Kelton Luke Miller Maddie Simens Amanda Askell Peter Welinder Paul Christiano Jan Leike and Ryan Lowe. 2022. Training language models to follow instructions with human feedback. arXiv:2203.02155 [cs.CL] https:\/\/arxiv.org\/abs\/2203.02155"},{"key":"e_1_2_2_79_1","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1212745110"},{"key":"e_1_2_2_80_1","doi-asserted-by":"publisher","DOI":"10.6087\/kcse.244"},{"key":"e_1_2_2_81_1","doi-asserted-by":"publisher","DOI":"10.1177\/0261927X16663257"},{"key":"e_1_2_2_82_1","doi-asserted-by":"publisher","DOI":"10.1145\/1921141.1921146"},{"key":"e_1_2_2_83_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11948-020-00228-y"},{"key":"e_1_2_2_84_1","series-title":"Television series","volume-title":"Cosmos: A Personal Voyage","author":"Sagan Carl","year":"1980","unstructured":"Carl Sagan, Ann Druyan, and Steven Soter. 1980. Cosmos: A Personal Voyage. Television series, 13 episodes."},{"key":"e_1_2_2_85_1","doi-asserted-by":"publisher","DOI":"10.1145\/3432908"},{"key":"e_1_2_2_86_1","doi-asserted-by":"publisher","DOI":"10.1145\/3411764.3445518"},{"key":"e_1_2_2_87_1","doi-asserted-by":"publisher","DOI":"10.1093\/oxfordhb\/9780190497620.013.5"},{"key":"e_1_2_2_88_1","doi-asserted-by":"publisher","DOI":"10.1145\/2818048.2819999"},{"key":"e_1_2_2_89_1","doi-asserted-by":"publisher","DOI":"10.1177\/1075547014529093"},{"key":"e_1_2_2_90_1","unstructured":"Times. 2024. Science Times. https:\/\/www.sciencetimes.com\/"},{"key":"e_1_2_2_91_1","doi-asserted-by":"publisher","DOI":"10.5555\/3600270.3602070"},{"key":"e_1_2_2_92_1","doi-asserted-by":"publisher","DOI":"10.1145\/3555591"},{"key":"e_1_2_2_93_1","doi-asserted-by":"publisher","DOI":"10.1145\/3290605.3300746"},{"key":"e_1_2_2_94_1","doi-asserted-by":"publisher","DOI":"10.1145\/2998181.2998364"},{"key":"e_1_2_2_95_1","doi-asserted-by":"publisher","DOI":"10.1145\/3637372"},{"key":"e_1_2_2_96_1","volume-title":"Proceedings of the ACM on Human-Computer Interaction CSCW","author":"Zhang Richard","year":"2025","unstructured":"Richard Zhang and Emoke-\u00c1gnes Horv\u00e1t. 2025. The Unwanted Dissemination of Science: The Usage of Academic Articles as Ammunition in Contested Discursive Arenas on Twitter. Proceedings of the ACM on Human-Computer Interaction CSCW (2025), 16 pages."},{"key":"e_1_2_2_97_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-demos.5"},{"key":"e_1_2_2_98_1","volume-title":"Personality Alignment of Large Language Models. In The Thirteenth International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=0DZEs8NpUH","author":"Zhu Minjun","year":"2025","unstructured":"Minjun Zhu, Yixuan Weng, Linyi Yang, and Yue Zhang. 2025. Personality Alignment of Large Language Models. In The Thirteenth International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=0DZEs8NpUH"},{"key":"e_1_2_2_99_1","doi-asserted-by":"publisher","DOI":"10.5210\/fm.v22i11.7866"},{"key":"e_1_2_2_100_1","volume-title":"The Thirteenth International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=2R7498e2Tx","author":"Zollo Thomas P","year":"2025","unstructured":"Thomas P Zollo, Andrew Wei Tung Siah, Naimeng Ye, Ang Li, and Hongseok Namkoong. 2025. PersonalLLM: Tailoring LLMs to Individual Preferences. In The Thirteenth International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=2R7498e2Tx"}],"container-title":["Proceedings of the ACM on Human-Computer Interaction"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3757660","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,17]],"date-time":"2025-10-17T01:56:41Z","timestamp":1760666201000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3757660"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,16]]},"references-count":100,"journal-issue":{"issue":"7","published-print":{"date-parts":[[2025,10,18]]}},"alternative-id":["10.1145\/3757660"],"URL":"https:\/\/doi.org\/10.1145\/3757660","relation":{},"ISSN":["2573-0142"],"issn-type":[{"type":"electronic","value":"2573-0142"}],"subject":[],"published":{"date-parts":[[2025,10,16]]},"assertion":[{"value":"2025-10-16","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}