{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,23]],"date-time":"2026-06-23T03:11:36Z","timestamp":1782184296459,"version":"3.54.5"},"publisher-location":"New York, NY, USA","reference-count":103,"publisher":"ACM","license":[{"start":{"date-parts":[[2027,3,22]],"date-time":"2027-03-22T00:00:00Z","timestamp":1805673600000},"content-version":"vor","delay-in-days":365,"URL":"http:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["2315937"],"award-info":[{"award-number":["2315937"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000185","name":"Defense Advanced Research Projects Agency","doi-asserted-by":"publisher","award":["HR00112520300"],"award-info":[{"award-number":["HR00112520300"]}],"id":[{"id":"10.13039\/100000185","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["2402647"],"award-info":[{"award-number":["2402647"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,3,23]]},"DOI":"10.1145\/3742413.3789091","type":"proceedings-article","created":{"date-parts":[[2026,3,3]],"date-time":"2026-03-03T11:32:24Z","timestamp":1772537544000},"page":"852-867","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["Interactive Reasoning: Visualizing and Controlling Chain-of-Thought Reasoning in Large Language Models"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8613-498X","authenticated-orcid":false,"given":"Rock Yuren","family":"Pang","sequence":"first","affiliation":[{"name":"University of Washington, Seattle, Washington, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2453-6315","authenticated-orcid":false,"given":"K. J. Kevin","family":"Feng","sequence":"additional","affiliation":[{"name":"University of Washington, Seattle, Washington, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4133-1987","authenticated-orcid":false,"given":"Shangbin","family":"Feng","sequence":"additional","affiliation":[{"name":"University of Washington, Seattle, Washington, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-7612-6224","authenticated-orcid":false,"given":"Chu","family":"Li","sequence":"additional","affiliation":[{"name":"University of Washington, Seattle, Washington, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1358-3551","authenticated-orcid":false,"given":"Weijia","family":"Shi","sequence":"additional","affiliation":[{"name":"University of Washington, Seattle, Washington, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4634-7128","authenticated-orcid":false,"given":"Yulia","family":"Tsvetkov","sequence":"additional","affiliation":[{"name":"University of Washington, Seattle, Washington, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6175-1655","authenticated-orcid":false,"given":"Jeffrey","family":"Heer","sequence":"additional","affiliation":[{"name":"University of Washington, Seattle, Washington, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7897-9325","authenticated-orcid":false,"given":"Katharina","family":"Reinecke","sequence":"additional","affiliation":[{"name":"University of Washington, Seattle, Washington, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,3,22]]},"reference":[{"key":"e_1_3_3_2_2_2","doi-asserted-by":"publisher","DOI":"10.1145\/3586183.3606719"},{"key":"e_1_3_3_2_3_2","unstructured":"Anthropic. 2025. Tracing the thoughts of a large language model. https:\/\/www.anthropic.com\/research\/tracing-thoughts-language-model. Accessed 2026-01-04."},{"key":"e_1_3_3_2_4_2","doi-asserted-by":"publisher","DOI":"10.1145\/3613904.3642016"},{"key":"e_1_3_3_2_5_2","unstructured":"Bowen Baker Joost Huizinga Leo Gao Zehao Dou Melody\u00a0Y. Guan Aleksander Madry Wojciech Zaremba Jakub Pachocki and David Farhi. 2025. Monitoring Reasoning Models for Misbehavior and the Risks of Promoting Obfuscation. arxiv:https:\/\/arXiv.org\/abs\/2503.11926\u00a0[cs.AI] https:\/\/arxiv.org\/abs\/2503.11926"},{"key":"e_1_3_3_2_6_2","doi-asserted-by":"crossref","unstructured":"Jeff Baker Donald Jones and Jim Burkman. 2009. Using visual representations of data to enhance sensemaking in data exploration tasks. Journal of the Association for Information Systems 10 7 (2009) 2.","DOI":"10.17705\/1jais.00204"},{"key":"e_1_3_3_2_7_2","doi-asserted-by":"publisher","DOI":"10.1145\/3411764.3445717"},{"key":"e_1_3_3_2_8_2","doi-asserted-by":"publisher","DOI":"10.1145\/3706598.3714097"},{"key":"e_1_3_3_2_9_2","doi-asserted-by":"publisher","unstructured":"Virginia Braun and Victoria\u00a0Clarke and. 2006. Using thematic analysis in psychology. Qualitative Research in Psychology 3 2 (2006) 77\u2013101. 10.1191\/1478088706qp063oa arXiv:https:\/\/www.tandfonline.com\/doi\/pdf\/10.1191\/1478088706qp063oa","DOI":"10.1191\/1478088706qp063oa"},{"key":"e_1_3_3_2_10_2","doi-asserted-by":"publisher","unstructured":"Zana Bu\u00e7inca Maja\u00a0Barbara Malaya and Krzysztof\u00a0Z. Gajos. 2021. To Trust or to Think: Cognitive Forcing Functions Can Reduce Overreliance on AI in AI-assisted Decision-making. Proc. ACM Hum.-Comput. Interact. 5 CSCW1 Article 188 (April 2021) 21\u00a0pages. 10.1145\/3449287","DOI":"10.1145\/3449287"},{"key":"e_1_3_3_2_11_2","doi-asserted-by":"publisher","DOI":"10.1109\/MODELS-C59198.2023.00097"},{"key":"e_1_3_3_2_12_2","unstructured":"Yanda Chen Joe Benton Ansh Radhakrishnan Jonathan Uesato Carson Denison John Schulman Arushi Somani Peter Hase Misha Wagner Fabien Roger Vlad Mikulik Samuel\u00a0R. Bowman Jan Leike Jared Kaplan and Ethan Perez. 2025. Reasoning Models Don\u2019t Always Say What They Think. arxiv:https:\/\/arXiv.org\/abs\/2505.05410\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/2505.05410"},{"key":"e_1_3_3_2_13_2","unstructured":"Yu\u00a0Ying Chiu Liwei Jiang and Yejin Choi. 2024. Dailydilemmas: Revealing value preferences of llms with quandaries of daily life. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2410.02683 (2024)."},{"key":"e_1_3_3_2_14_2","doi-asserted-by":"publisher","DOI":"10.1145\/3544548.3580969"},{"key":"e_1_3_3_2_15_2","unstructured":"Jillian Fisher Shangbin Feng Robert Aron Thomas Richardson Yejin Choi Daniel\u00a0W. Fisher Jennifer Pan Yulia Tsvetkov and Katharina Reinecke. 2025. Biased AI can Influence Political Decision-Making. arxiv:https:\/\/arXiv.org\/abs\/2410.06415\u00a0[cs.HC] https:\/\/arxiv.org\/abs\/2410.06415"},{"key":"e_1_3_3_2_16_2","volume-title":"Argumentation and debate: Critical thinking for reasoned decision making","author":"Freeley Austin\u00a0J","year":"2009","unstructured":"Austin\u00a0J Freeley. 2009. Argumentation and debate: Critical thinking for reasoned decision making."},{"key":"e_1_3_3_2_17_2","doi-asserted-by":"publisher","DOI":"10.1145\/3613904.3642139"},{"key":"e_1_3_3_2_18_2","unstructured":"Daya Guo Dejian Yang Haowei Zhang Junxiao Song Ruoyu Zhang Runxin Xu Qihao Zhu Shirong Ma Peiyi Wang Xiao Bi et\u00a0al. 2025. DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning. arxiv:https:\/\/arXiv.org\/abs\/2501.12948\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/2501.12948"},{"key":"e_1_3_3_2_19_2","volume-title":"Ethical decision making in everyday work situations","author":"Guy Mary\u00a0E","year":"1990","unstructured":"Mary\u00a0E Guy. 1990. Ethical decision making in everyday work situations. Bloomsbury Publishing."},{"key":"e_1_3_3_2_20_2","doi-asserted-by":"publisher","DOI":"10.1145\/3613904.3642834"},{"key":"e_1_3_3_2_21_2","doi-asserted-by":"crossref","unstructured":"Jeffrey Heer. 2019. Agency plus automation: Designing artificial intelligence into interactive systems. Proceedings of the National Academy of Sciences 116 6 (2019) 1844\u20131850.","DOI":"10.1073\/pnas.1807184115"},{"key":"e_1_3_3_2_22_2","unstructured":"Dan Hendrycks Collin Burns Steven Basart Andrew Critch Jerry Li Dawn Song and Jacob Steinhardt. 2020. Aligning ai with shared human values. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2008.02275 (2020)."},{"key":"e_1_3_3_2_23_2","doi-asserted-by":"crossref","unstructured":"Ari Holtzman Peter West Vered Shwartz Yejin Choi and Luke Zettlemoyer. 2021. Surface form competition: Why the highest probability answer isn\u2019t always right. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2104.08315 (2021).","DOI":"10.18653\/v1\/2021.emnlp-main.564"},{"key":"e_1_3_3_2_24_2","doi-asserted-by":"publisher","DOI":"10.1145\/3613904.3641895"},{"key":"e_1_3_3_2_25_2","doi-asserted-by":"publisher","DOI":"10.1145\/302979.303030"},{"key":"e_1_3_3_2_26_2","unstructured":"Aaron Jaech Adam Kalai Adam Lerer Adam Richardson Ahmed El-Kishky Aiden Low Alec Helyar Aleksander Madry Alex Beutel Alex Carney et\u00a0al. 2024. OpenAI o1 System Card. arxiv:https:\/\/arXiv.org\/abs\/2412.16720\u00a0[cs.AI] https:\/\/arxiv.org\/abs\/2412.16720"},{"key":"e_1_3_3_2_27_2","doi-asserted-by":"publisher","DOI":"10.1145\/3586183.3606737"},{"key":"e_1_3_3_2_28_2","unstructured":"Zhuohang Jiang Pangjing Wu Ziran Liang Peter\u00a0Q Chen Xu Yuan Ye Jia Jiancheng Tu Chen Li Peter\u00a0HF Ng and Qing Li. 2025. HiBench: Benchmarking LLMs Capability on Hierarchical Structure Reasoning. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2503.00912 (2025)."},{"key":"e_1_3_3_2_29_2","doi-asserted-by":"crossref","unstructured":"Philip\u00a0N Johnson-Laird Sangeet\u00a0S Khemlani and Geoffrey\u00a0P Goodwin. 2015. Logic probability and human reasoning. Trends in cognitive sciences 19 4 (2015) 201\u2013214.","DOI":"10.1016\/j.tics.2015.02.006"},{"key":"e_1_3_3_2_30_2","doi-asserted-by":"publisher","DOI":"10.1145\/3613905.3650755"},{"key":"e_1_3_3_2_31_2","doi-asserted-by":"publisher","DOI":"10.1145\/3706599.3719830"},{"key":"e_1_3_3_2_32_2","doi-asserted-by":"publisher","DOI":"10.1145\/3654777.3676345"},{"key":"e_1_3_3_2_33_2","doi-asserted-by":"publisher","DOI":"10.1145\/3630106.3658941"},{"key":"e_1_3_3_2_34_2","doi-asserted-by":"publisher","DOI":"10.1145\/3706598.3714020"},{"key":"e_1_3_3_2_35_2","doi-asserted-by":"publisher","DOI":"10.1145\/3544548.3581001"},{"key":"e_1_3_3_2_36_2","doi-asserted-by":"publisher","DOI":"10.1145\/3613904.3642216"},{"key":"e_1_3_3_2_37_2","doi-asserted-by":"publisher","DOI":"10.1145\/3640543.3645148"},{"key":"e_1_3_3_2_38_2","unstructured":"Takeshi Kojima Shixiang\u00a0Shane Gu Machel Reid Yutaka Matsuo and Yusuke Iwasawa. 2023. Large Language Models are Zero-Shot Reasoners. arxiv:https:\/\/arXiv.org\/abs\/2205.11916\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/2205.11916"},{"key":"e_1_3_3_2_39_2","doi-asserted-by":"publisher","DOI":"10.1145\/3613904.3642830"},{"key":"e_1_3_3_2_40_2","doi-asserted-by":"publisher","DOI":"10.1145\/3706598.3713778"},{"key":"e_1_3_3_2_41_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.703"},{"key":"e_1_3_3_2_42_2","unstructured":"Diya Li Yue Zhao Zhifang Wang Calvin Jung and Zhe Zhang. 2024. Large Language Model-Driven Structured Output: A Comprehensive Benchmark and Spatial Data Generation Framework. ISPRS International Journal of Geo-Information (2024). https:\/\/api.semanticscholar.org\/CorpusID:273976782"},{"key":"e_1_3_3_2_43_2","unstructured":"Jiacheng Liu Andrew Cohen Ramakanth Pasunuru Yejin Choi Hannaneh Hajishirzi and Asli Celikyilmaz. 2024. Don\u2019t throw away your value model! Generating more preferable text with Value-Guided Monte-Carlo Tree Search decoding. arxiv:https:\/\/arXiv.org\/abs\/2309.15028\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/2309.15028"},{"key":"e_1_3_3_2_44_2","doi-asserted-by":"crossref","unstructured":"Nelson\u00a0F Liu Kevin Lin John Hewitt Ashwin Paranjape Michele Bevilacqua Fabio Petroni and Percy Liang. 2024. Lost in the middle: How language models use long contexts. Transactions of the Association for Computational Linguistics 12 (2024) 157\u2013173.","DOI":"10.1162\/tacl_a_00638"},{"key":"e_1_3_3_2_45_2","unstructured":"Xingyu\u00a0Bruce Liu Haijun Xia and Xiang\u00a0Anthony Chen. 2025. Interacting with Thoughtful AI. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2502.18676 (2025)."},{"key":"e_1_3_3_2_46_2","doi-asserted-by":"publisher","unstructured":"Yang Liu Alex Kale Tim Althoff and Jeffrey Heer. 2021. Boba: Authoring and Visualizing Multiverse Analyses. IEEE Transactions on Visualization and Computer Graphics 27 2 (2021) 1753\u20131763. 10.1109\/TVCG.2020.3028985","DOI":"10.1109\/TVCG.2020.3028985"},{"key":"e_1_3_3_2_47_2","doi-asserted-by":"publisher","DOI":"10.1145\/3613904.3642462"},{"key":"e_1_3_3_2_48_2","unstructured":"Katelyn\u00a0Xiaoying Mei Rock\u00a0Yuren Pang Alex Lyford Lucy\u00a0Lu Wang and Katharina Reinecke. 2025. Passing the Buck to AI: How Individuals\u2019 Decision-Making Patterns Affect Reliance on AI. arxiv:https:\/\/arXiv.org\/abs\/2505.01537\u00a0[cs.HC] https:\/\/arxiv.org\/abs\/2505.01537"},{"key":"e_1_3_3_2_49_2","doi-asserted-by":"crossref","unstructured":"Sewon Min Xinxi Lyu Ari Holtzman Mikel Artetxe Mike Lewis Hannaneh Hajishirzi and Luke Zettlemoyer. 2022. Rethinking the Role of Demonstrations: What Makes In-Context Learning Work?ArXiv abs\/2202.12837 (2022). https:\/\/api.semanticscholar.org\/CorpusID:247155069","DOI":"10.18653\/v1\/2022.emnlp-main.759"},{"key":"e_1_3_3_2_50_2","unstructured":"Iman Mirzadeh Keivan Alizadeh Hooman Shahrokhi Oncel Tuzel Samy Bengio and Mehrdad Farajtabar. 2024. Gsm-symbolic: Understanding the limitations of mathematical reasoning in large language models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2410.05229 (2024)."},{"key":"e_1_3_3_2_51_2","doi-asserted-by":"crossref","unstructured":"Niklas Muennighoff Zitong Yang Weijia Shi Xiang\u00a0Lisa Li Li Fei-Fei Hannaneh Hajishirzi Luke Zettlemoyer Percy Liang Emmanuel Cand\u00e8s and Tatsunori Hashimoto. 2025. s1: Simple test-time scaling. arxiv:https:\/\/arXiv.org\/abs\/2501.19393\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/2501.19393","DOI":"10.18653\/v1\/2025.emnlp-main.1025"},{"key":"e_1_3_3_2_52_2","unstructured":"Richard Nordquist. 2019. What is deductive reasoning?https:\/\/www.thoughtco.com\/deduction-logic-and-rhetoric-1690422"},{"key":"e_1_3_3_2_53_2","unstructured":"OpenAI. 2025. Detecting Misbehavior in Frontier Reasoning Models. https:\/\/openai.com\/index\/chain-of-thought-monitoring\/. Accessed Apr 08 2025."},{"key":"e_1_3_3_2_54_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.146"},{"key":"e_1_3_3_2_55_2","doi-asserted-by":"publisher","DOI":"10.1145\/3706598.3713726"},{"key":"e_1_3_3_2_56_2","doi-asserted-by":"crossref","unstructured":"Joon\u00a0Sung Park Rick Barber Alex Kirlik and Karrie Karahalios. 2019. A slow algorithm improves users\u2019 assessments of the algorithm\u2019s accuracy. Proceedings of the ACM on Human-Computer Interaction 3 CSCW (2019) 1\u201315.","DOI":"10.1145\/3359204"},{"key":"e_1_3_3_2_57_2","doi-asserted-by":"crossref","unstructured":"Andreas Peldszus and Manfred Stede. 2013. From argument diagrams to argumentation mining in texts: A survey. International Journal of Cognitive Informatics and Natural Intelligence (IJCINI) 7 1 (2013) 1\u201331.","DOI":"10.4018\/jcini.2013010101"},{"key":"e_1_3_3_2_58_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.899"},{"key":"e_1_3_3_2_59_2","doi-asserted-by":"publisher","unstructured":"Marc Pinski and Alexander Benlian. 2024. AI literacy for users \u2013 A comprehensive review and future research directions of learning methods components and effects. Computers in Human Behavior: Artificial Humans 2 1 (2024) 100062. 10.1016\/j.chbah.2024.100062","DOI":"10.1016\/j.chbah.2024.100062"},{"key":"e_1_3_3_2_60_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.378"},{"key":"e_1_3_3_2_61_2","doi-asserted-by":"publisher","DOI":"10.1145\/3706598.3714057"},{"key":"e_1_3_3_2_62_2","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-63938-1_67"},{"key":"e_1_3_3_2_63_2","unstructured":"Sebastian Raschka. 2025. Understanding reasoning llms. https:\/\/magazine.sebastianraschka.com\/p\/understanding-reasoning-llms"},{"key":"e_1_3_3_2_64_2","doi-asserted-by":"crossref","unstructured":"Chris Reed Douglas Walton and Fabrizio Macagno. 2007. Argument diagramming in logic law and artificial intelligence. The Knowledge Engineering Review 22 1 (2007) 87\u2013109.","DOI":"10.1017\/S0269888907001051"},{"key":"e_1_3_3_2_65_2","doi-asserted-by":"crossref","unstructured":"Edward\u00a0M. Reingold and John\u00a0S. Tilford. 1981. Tidier drawings of trees. IEEE Transactions on software Engineering2 (1981) 223\u2013228.","DOI":"10.1109\/TSE.1981.234519"},{"key":"e_1_3_3_2_66_2","volume-title":"International Conference on Learning Representations","author":"Sanh Victor","year":"2022","unstructured":"Victor Sanh, Albert Webson, Colin Raffel, Stephen Bach, et\u00a0al. 2022. Multitask Prompted Training Enables Zero-Shot Task Generalization. In International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=9Vrb9D0WI4"},{"key":"e_1_3_3_2_67_2","doi-asserted-by":"publisher","DOI":"10.1145\/3581641.3584066"},{"key":"e_1_3_3_2_68_2","doi-asserted-by":"publisher","DOI":"10.1145\/3613904.3642459"},{"key":"e_1_3_3_2_69_2","doi-asserted-by":"crossref","unstructured":"Ben Shneiderman. 1983. Direct manipulation: A step beyond programming languages. Computer 16 08 (1983) 57\u201369.","DOI":"10.1109\/MC.1983.1654471"},{"key":"e_1_3_3_2_70_2","doi-asserted-by":"publisher","DOI":"10.1016\/B978-155860915-0\/50046-9"},{"key":"e_1_3_3_2_71_2","doi-asserted-by":"crossref","unstructured":"Ben Shneiderman. 2020. Human-Centered Artificial Intelligence: Reliable Safe & Trustworthy. International Journal of Human\u2013Computer Interaction 36 (2020) 495 \u2013 504. https:\/\/api.semanticscholar.org\/CorpusID:211259461","DOI":"10.1080\/10447318.2020.1741118"},{"key":"e_1_3_3_2_72_2","unstructured":"Connor Shorten Charles Pierse Thomas\u00a0Benjamin Smith Erika Cardenas Akanksha Sharma John Trengrove and Bob van Luijt. 2024. StructuredRAG: JSON Response Formatting with Large Language Models. ArXiv abs\/2408.11061 (2024). https:\/\/api.semanticscholar.org\/CorpusID:271916259"},{"key":"e_1_3_3_2_73_2","volume-title":"The Thirteenth International Conference on Learning Representations","author":"Snell Charlie\u00a0Victor","year":"2025","unstructured":"Charlie\u00a0Victor Snell, Jaehoon Lee, Kelvin Xu, and Aviral Kumar. 2025. Scaling LLM Test-Time Compute Optimally Can be More Effective than Scaling Parameters for Reasoning. In The Thirteenth International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=4FWAwZtd2n"},{"key":"e_1_3_3_2_74_2","doi-asserted-by":"crossref","unstructured":"Paul\u00a0M Sniderman and Sean\u00a0M Theriault. 2004. The structure of political argument and the logic of issue framing. Studies in public opinion: Attitudes nonattitudes measurement error and change 3 03 (2004) 133\u201365.","DOI":"10.1515\/9780691188386-007"},{"key":"e_1_3_3_2_75_2","unstructured":"Aarohi Srivastava Abhinav Rastogi Abhishek Rao Abu Awal\u00a0Md Shoeb Abubakar Abid Adam Fisch Adam\u00a0R Brown Adam Santoro Aditya Gupta Adri\u00e0 Garriga-Alonso et\u00a0al. 2022. Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models."},{"key":"e_1_3_3_2_76_2","doi-asserted-by":"crossref","unstructured":"Christian Stab and Iryna Gurevych. 2017. Parsing argumentation structures in persuasive essays. Computational Linguistics 43 3 (2017) 619\u2013659.","DOI":"10.1162\/COLI_a_00295"},{"key":"e_1_3_3_2_77_2","doi-asserted-by":"publisher","DOI":"10.1145\/3586183.3606756"},{"key":"e_1_3_3_2_78_2","doi-asserted-by":"publisher","DOI":"10.1145\/3640543.3645206"},{"key":"e_1_3_3_2_79_2","doi-asserted-by":"crossref","unstructured":"Peter Szolovits Ramesh\u00a0S Patil and William\u00a0B Schwartz. 1988. Artificial intelligence in medical diagnosis. Annals of internal medicine 108 1 (1988) 80\u201387.","DOI":"10.7326\/0003-4819-108-1-80"},{"key":"e_1_3_3_2_80_2","unstructured":"Together AI. 2025. https:\/\/api.together.xyz\/. Accessed April 08 2025."},{"key":"e_1_3_3_2_81_2","doi-asserted-by":"crossref","unstructured":"Douglas\u00a0N Walton. 1990. What is reasoning? What is an argument?The journal of Philosophy 87 8 (1990) 399\u2013419.","DOI":"10.2307\/2026735"},{"key":"e_1_3_3_2_82_2","unstructured":"Douglas\u00a0N Walton and Lynn\u00a0M Batten. 1984. Games graphs and circular arguments. Logique et Analyse 27 106 (1984) 133\u2013164."},{"key":"e_1_3_3_2_83_2","doi-asserted-by":"crossref","unstructured":"Heng Wang Shangbin Feng Tianxing He Zhaoxuan Tan Xiaochuang Han and Yulia Tsvetkov. 2023. Can language models solve graph problems in natural language?Advances in Neural Information Processing Systems 36 (2023) 30840\u201330861.","DOI":"10.52202\/075280-1345"},{"key":"e_1_3_3_2_84_2","doi-asserted-by":"publisher","DOI":"10.1145\/3397481.3450650"},{"key":"e_1_3_3_2_85_2","unstructured":"Yizhong Wang Swaroop Mishra et\u00a0al. 2022. Super-naturalinstructions: Generalization via declarative instructions on 1600+ nlp tasks. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2204.07705 (2022)."},{"key":"e_1_3_3_2_86_2","doi-asserted-by":"publisher","DOI":"10.1145\/3613904.3642335"},{"key":"e_1_3_3_2_87_2","doi-asserted-by":"crossref","unstructured":"Jason Wei Xuezhi Wang Dale Schuurmans Maarten Bosma Fei Xia Ed Chi Quoc\u00a0V Le Denny Zhou et\u00a0al. 2022. Chain-of-thought prompting elicits reasoning in large language models. Advances in neural information processing systems 35 (2022) 24824\u201324837.","DOI":"10.52202\/068431-1800"},{"key":"e_1_3_3_2_88_2","doi-asserted-by":"publisher","DOI":"10.1145\/3491101.3519729"},{"key":"e_1_3_3_2_89_2","doi-asserted-by":"publisher","DOI":"10.1145\/3491102.3517582"},{"key":"e_1_3_3_2_90_2","unstructured":"Yangzhen Wu Zhiqing Sun Shanda Li Sean Welleck and Yiming Yang. 2024. Inference scaling laws: An empirical analysis of compute-optimal inference for problem-solving with language models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2408.00724 (2024)."},{"key":"e_1_3_3_2_91_2","unstructured":"Yuxi Xie Anirudh Goyal Wenyue Zheng Min-Yen Kan Timothy\u00a0P Lillicrap Kenji Kawaguchi and Michael Shieh. 2024. Monte carlo tree search boosts reasoning via iterative preference learning. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2405.00451 (2024)."},{"key":"e_1_3_3_2_92_2","volume-title":"Thirty-seventh Conference on Neural Information Processing Systems","author":"Yao Shunyu","year":"2023","unstructured":"Shunyu Yao, Dian Yu, Jeffrey Zhao, Izhak Shafran, Thomas\u00a0L. Griffiths, Yuan Cao, and Karthik\u00a0R Narasimhan. 2023. Tree of Thoughts: Deliberate Problem Solving with Large Language Models. In Thirty-seventh Conference on Neural Information Processing Systems. https:\/\/openreview.net\/forum?id=5Xc1ecxO1h"},{"key":"e_1_3_3_2_93_2","volume-title":"The eleventh international conference on learning representations","author":"Yao Shunyu","year":"2022","unstructured":"Shunyu Yao, Jeffrey Zhao, Dian Yu, Nan Du, Izhak Shafran, Karthik\u00a0R Narasimhan, and Yuan Cao. 2022. React: Synergizing reasoning and acting in language models. In The eleventh international conference on learning representations."},{"key":"e_1_3_3_2_94_2","doi-asserted-by":"publisher","DOI":"10.1145\/3654777.3676357"},{"key":"e_1_3_3_2_95_2","doi-asserted-by":"publisher","DOI":"10.1145\/3290605.3300509"},{"key":"e_1_3_3_2_96_2","doi-asserted-by":"publisher","unstructured":"Fei Yu Hongbo Zhang Prayag Tiwari and Benyou Wang. 2024. Natural Language Reasoning A Survey. ACM Comput. Surv. 56 12 Article 304 (Oct. 2024) 39\u00a0pages. 10.1145\/3664194","DOI":"10.1145\/3664194"},{"key":"e_1_3_3_2_97_2","doi-asserted-by":"crossref","unstructured":"Fei Yu Hongbo Zhang Prayag Tiwari and Benyou Wang. 2024. Natural language reasoning a survey. Comput. Surveys 56 12 (2024) 1\u201339.","DOI":"10.1145\/3664194"},{"key":"e_1_3_3_2_98_2","doi-asserted-by":"publisher","DOI":"10.1145\/3544548.3581388"},{"key":"e_1_3_3_2_99_2","doi-asserted-by":"publisher","DOI":"10.1145\/2998181.2998235"},{"key":"e_1_3_3_2_100_2","unstructured":"Qiyuan Zhang Fuyuan Lyu Zexu Sun Lei Wang Weixu Zhang Wenyue Hua Haolun Wu Zhihan Guo Yufei Wang Niklas Muennighoff Irwin King Xue Liu and Chen Ma. 2025. A Survey on Test-Time Scaling in Large Language Models: What How Where and How Well? arxiv:https:\/\/arXiv.org\/abs\/2503.24235\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/2503.24235"},{"key":"e_1_3_3_2_101_2","doi-asserted-by":"publisher","DOI":"10.1145\/3351095.3372852"},{"key":"e_1_3_3_2_102_2","doi-asserted-by":"publisher","unstructured":"Haiyan Zhao Hanjie Chen Fan Yang Ninghao Liu Huiqi Deng Hengyi Cai Shuaiqiang Wang Dawei Yin and Mengnan Du. 2024. Explainability for Large Language Models: A Survey. ACM Trans. Intell. Syst. Technol. 15 2 Article 20 (Feb. 2024) 38\u00a0pages. 10.1145\/3639372","DOI":"10.1145\/3639372"},{"key":"e_1_3_3_2_103_2","unstructured":"Wenting Zhao Xiang Ren Jack Hessel Claire Cardie Yejin Choi and Yuntian Deng. 2024. Wildchat: 1m chatgpt interaction logs in the wild. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2405.01470 (2024)."},{"key":"e_1_3_3_2_104_2","unstructured":"Zhaocheng Zhu Yuan Xue Xinyun Chen Denny Zhou Jian Tang Dale Schuurmans and Hanjun Dai. 2023. Large language models can learn rules. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2310.07064 (2023)."}],"event":{"name":"IUI '26: 31st International Conference on Intelligent User Interfaces","location":"Paphos Cyprus","acronym":"IUI '26","sponsor":["SIGCHI ACM Special Interest Group on Computer-Human Interaction","SIGAI ACM Special Interest Group on Artificial Intelligence"]},"container-title":["Proceedings of the 31st International Conference on Intelligent User Interfaces"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/abs\/10.1145\/3742413.3789091","content-type":"text\/html","content-version":"vor","intended-application":"syndication"}],"deposited":{"date-parts":[[2026,3,14]],"date-time":"2026-03-14T12:57:26Z","timestamp":1773493046000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3742413.3789091"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,22]]},"references-count":103,"alternative-id":["10.1145\/3742413.3789091","10.1145\/3742413"],"URL":"https:\/\/doi.org\/10.1145\/3742413.3789091","relation":{},"subject":[],"published":{"date-parts":[[2026,3,22]]},"assertion":[{"value":"2026-03-22","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}