{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,29]],"date-time":"2026-06-29T18:44:53Z","timestamp":1782758693113,"version":"3.54.5"},"publisher-location":"New York, NY, USA","reference-count":121,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,6,25]],"date-time":"2026-06-25T00:00:00Z","timestamp":1782345600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"Advanced Research Projects Agency for Health (ARPA-H)","award":["AY2AX000044"],"award-info":[{"award-number":["AY2AX000044"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,6,25]]},"DOI":"10.1145\/3805689.3806456","type":"proceedings-article","created":{"date-parts":[[2026,6,29]],"date-time":"2026-06-29T17:52:08Z","timestamp":1782755528000},"page":"6702-6722","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Beyond the Response: Examining Reasoning and Execution Fidelity in Large Language Models for Mental Health"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-7962-5792","authenticated-orcid":false,"given":"Sarvech","family":"Qadir","sequence":"first","affiliation":[{"name":"Computer Science, Vanderbilt University, Nashville, Tennessee, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6950-6948","authenticated-orcid":false,"given":"Congning","family":"Ni","sequence":"additional","affiliation":[{"name":"Vanderbilt University Medical Center, Nashville, Tennessee, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-8055-9539","authenticated-orcid":false,"given":"Mihir Sachin","family":"Vaidya","sequence":"additional","affiliation":[{"name":"Vanderbilt University Medical Center, Nashville, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2589-834X","authenticated-orcid":false,"given":"Hyeyoung","family":"Ryu","sequence":"additional","affiliation":[{"name":"Vanderbilt University Medical Center, Nashville, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1622-6744","authenticated-orcid":false,"given":"Shelagh A","family":"Mulvaney","sequence":"additional","affiliation":[{"name":"Vanderbilt University, Nashville, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9795-9063","authenticated-orcid":false,"given":"Murat","family":"Kantarcioglu","sequence":"additional","affiliation":[{"name":"Virginia Polytechnic Institute and State University, Blacksburg, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0415-4301","authenticated-orcid":false,"given":"Laurie Lovett","family":"Novak","sequence":"additional","affiliation":[{"name":"Vanderbilt University Medical Center, Nashville, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3040-5175","authenticated-orcid":false,"given":"Bradley","family":"Malin","sequence":"additional","affiliation":[{"name":"Vanderbilt University Medical Center, Nashville, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5895-7460","authenticated-orcid":false,"given":"Susannah Leigh","family":"Rose","sequence":"additional","affiliation":[{"name":"Vanderbilt University Medical Center, Nashville, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3075-1337","authenticated-orcid":false,"given":"Zhijun","family":"Yin","sequence":"additional","affiliation":[{"name":"Vanderbilt University Medical Center, Nashville, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,6,25]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"How about kind of generating hedges using end-to-end neural models? arXiv preprint arXiv:2306.14696","author":"Abulimiti Alafate","year":"2023","unstructured":"Alafate Abulimiti, Chlo\u00e9 Clavel, and Justine Cassell. 2023. How about kind of generating hedges using end-to-end neural models? arXiv preprint arXiv:2306.14696 (2023)."},{"key":"e_1_3_2_1_2_1","volume-title":"Speceval: Evaluating model adherence to behavior specifications. arXiv preprint arXiv:2509.02464","author":"Ahmed Ahmed","year":"2025","unstructured":"Ahmed Ahmed, Kevin Klyman, Yi Zeng, Sanmi Koyejo, and Percy Liang. 2025. Speceval: Evaluating model adherence to behavior specifications. arXiv preprint arXiv:2509.02464 (2025)."},{"key":"e_1_3_2_1_3_1","volume-title":"Dina Abdel Salam El-Dakhs, and Ayah Mustafa","author":"Alghazo Sharif","year":"2025","unstructured":"Sharif Alghazo, Ghaleb Rababah, Dina Abdel Salam El-Dakhs, and Ayah Mustafa. 2025. Engagement strategies in human-written and AI-generated academic essays: A corpus-based study. Ampersand (2025), 100237."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/2998181.2998243"},{"key":"e_1_3_2_1_5_1","volume-title":"Not Longer. arXiv preprint arXiv:2502.15631","author":"Ballon Marthe","year":"2025","unstructured":"Marthe Ballon, Andres Algaba, and Vincent Ginis. 2025. The Relationship Between Reasoning and Performance in Large Language Models-o3 (mini) Thinks Harder, Not Longer. arXiv preprint arXiv:2502.15631 (2025)."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/3715275.3732093"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.4324\/9781003320609-52"},{"key":"e_1_3_2_1_8_1","unstructured":"Suhas Bettapalli Nagaraj. 2025. Generative Human-Centered AI in Mental Health: Supporting Therapeutic Fidelity and Empathy in Interactions. (2025)."},{"key":"e_1_3_2_1_9_1","unstructured":"Xiao Bi Deli Chen Guanting Chen Shanhuang Chen Damai Dai Chengqi Deng Honghui Ding Kai Dong Qiushi Du Zhe Fu et al. 2024. Deepseek llm: Scaling open-source language models with longtermism. arXiv preprint arXiv:2401.02954 (2024)."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/3706598.3714097"},{"key":"e_1_3_2_1_11_1","volume-title":"Using thematic analysis in psychology. Qualitative research in psychology 3, 2","author":"Braun Virginia","year":"2006","unstructured":"Virginia Braun and Victoria Clarke. 2006. Using thematic analysis in psychology. Qualitative research in psychology 3, 2 (2006), 77\u2013101."},{"key":"e_1_3_2_1_12_1","series-title":"Series (2004-004) 9","volume-title":"Renyi entropy, and information. Statistics and Inf","author":"Bromiley PA","year":"2004","unstructured":"PA Bromiley, NA Thacker, and E Bouhova-Thacker. 2004. Shannon entropy, Renyi entropy, and information. Statistics and Inf. Series (2004-004) 9, 2004 (2004), 2\u20138."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"crossref","unstructured":"Andreas Bucher Sarah Egger Inna Vashkite Wenyuan Wu and Gerhard Schwabe. 2025. \u201cIt's Not Only Attention We Need\u201d: Systematic Review of Large Language Models in Mental Health Care. JMIR mental health 12 (2025) e78410.","DOI":"10.2196\/78410"},{"key":"e_1_3_2_1_14_1","unstructured":"Ana-Mar\u00eda Bucur Cosma. 2025. Computational Approaches to Mental Health Disorders Detection from Social Media Texts Images and Videos. (2025)."},{"key":"e_1_3_2_1_15_1","volume-title":"Can You Trust an LLM with Your Life-Changing Decision? An Investigation into AI High-Stakes Responses. arXiv preprint arXiv:2507.21132","author":"Cahyono Joshua Adrian","year":"2025","unstructured":"Joshua Adrian Cahyono and Saran Subramanian. 2025. Can You Trust an LLM with Your Life-Changing Decision? An Investigation into AI High-Stakes Responses. arXiv preprint arXiv:2507.21132 (2025)."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/3630106.3659037"},{"key":"e_1_3_2_1_17_1","volume-title":"Methods in predictive techniques for mental health status on social media: a critical review. NPJ digital medicine 3, 1","author":"Chancellor Stevie","year":"2020","unstructured":"Stevie Chancellor and Munmun De Choudhury. 2020. Methods in predictive techniques for mental health status on social media: a critical review. NPJ digital medicine 3, 1 (2020), 43."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/3715275.3732063"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"crossref","unstructured":"Aaron Chase Amoreena Most Andrea Sikora Susan E Smith John W Devlin Shaochen Xu Tianming Liu and Brian Murray. 2025. Evaluation of large language models' ability to identify clinically relevant drug-drug interactions and generate high-quality clinical pharmacotherapy recommendations. American Journal of Health-System Pharmacy (2025) zxaf168.","DOI":"10.1093\/ajhp\/zxaf168"},{"key":"e_1_3_2_1_20_1","volume-title":"Marius Funk, Lynn Greschner, Roberto Hung, Stina Klein, et al.","author":"Chavan Vivek","year":"2025","unstructured":"Vivek Chavan, Arsen Cenaj, Shuyuan Shen, Ariane Bar, Srishti Binwani, Tommaso Del Becaro, Marius Funk, Lynn Greschner, Roberto Hung, Stina Klein, et al. 2025. Feeling machines: ethics, culture, and the rise of emotional AI. arXiv preprint arXiv.2506. 12437 (2025)."},{"key":"e_1_3_2_1_21_1","volume-title":"A framework for evaluating appropriateness, trustworthiness, and safety in mental wellness ai chatbots. arXiv preprint arXiv:2407.11387","author":"Chen Lucia","year":"2024","unstructured":"Lucia Chen, David A Preece, Pilleriin Sikka, James J Gross, and Ben Krause. 2024. A framework for evaluating appropriateness, trustworthiness, and safety in mental wellness ai chatbots. arXiv preprint arXiv:2407.11387 (2024)."},{"key":"e_1_3_2_1_22_1","volume-title":"Towards reasoning era: A survey of long chain-of-thought for reasoning large language models. arXiv preprint arXiv:2503.09567","author":"Chen Qiguang","year":"2025","unstructured":"Qiguang Chen, Libo Qin, Jinhao Liu, Dengyun Peng, Jiannan Guan, Peng Wang, Mengkang Hu, Yuhang Zhou, Te Gao, and Wanxiang Che. 2025. Towards reasoning era: A survey of long chain-of-thought for reasoning large language models. arXiv preprint arXiv:2503.09567 (2025)."},{"key":"e_1_3_2_1_23_1","volume-title":"Tianle Li, Dacheng Li, Hao Zhang, Banghua Zhu, Michael Jordan, Joseph E Gonzalez, et al.","author":"Chiang Wei-Lin","year":"2024","unstructured":"Wei-Lin Chiang, Lianmin Zheng, Ying Sheng, Anastasios Nikolas Angelopoulos, Tianle Li, Dacheng Li, Hao Zhang, Banghua Zhu, Michael Jordan, Joseph E Gonzalez, et al. 2024. Chatbot arena: An open platform for evaluating llms by human preference. arXiv preprint arXiv:2403.04132 (2024)."},{"key":"e_1_3_2_1_24_1","volume-title":"Abdel-Badih Ariss, Marc Ghanem, et al.","author":"Chung Philip","year":"2025","unstructured":"Philip Chung, Akshay Swaminathan, Alex J Goodell, Yeasul Kim, S Momsen Reincke, Lichy Han, Ben Deverett, Mohammad Amin Sadeghi, Abdel-Badih Ariss, Marc Ghanem, et al. 2025. Verifact: Verifying facts in llm-generated clinical text with electronic health records. arXiv preprint arXiv 2501.16672 (2025)."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/3442188.3445921"},{"key":"e_1_3_2_1_26_1","unstructured":"Gheorghe Comanici Eric Bieber Mike Schaekermann Ice Pasupat Noveen Sachdeva Inderjit Dhillon Marcel Blistein Ori Ram Dan Zhang Evan Rosen et al. 2025. Gemini 2.5: Pushing the frontier with advanced reasoning multimodality long context and next generation agentic capabilities. arXiv preprint arXiv:2507.06261 (2025)."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1177\/1536867X1501500117"},{"key":"e_1_3_2_1_28_1","unstructured":"Abhimanyu Dubey Abhinav Jauhri Abhinav Pandey Abhishek Kadian Ahmad Al-Dahle Aiesha Letman Akhil Mathur Alan Schelten Amy Yang Angela Fan et al. 2024. The llama 3 herd of models. arXiv e-prints (2024) arXiv-2407."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1007\/s43681-025-00758-w"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/3706599.3720191"},{"key":"e_1_3_2_1_31_1","volume-title":"Towards trustworthy ai: A review of ethical and robust large language models. arXiv preprint arXiv 2407.13934","author":"Ferdaus Md Meftahul","year":"2024","unstructured":"Md Meftahul Ferdaus, Mahdi Abdelguerfi, Elias Ioup, Kendall N Niles, Ken Pathak, and Steven Sloan. 2024. Towards trustworthy ai: A review of ethical and robust large language models. arXiv preprint arXiv 2407.13934 (2024)."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/3715275.3732091"},{"key":"e_1_3_2_1_33_1","volume-title":"An Innovative Solution to Design Problems: Applying the Chain-of-Thought Technique to Integrate LLM-based Agents with Concept Generation Methods","author":"Ge Shijun","year":"2024","unstructured":"Shijun Ge, Yuanbo Sun, Yin Cui, and Dapeng Wei. 2024. An Innovative Solution to Design Problems: Applying the Chain-of-Thought Technique to Integrate LLM-based Agents with Concept Generation Methods. IEEE Access (2024)."},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/3715275.3732004"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-023-02412-6"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/3715275.3732181"},{"key":"e_1_3_2_1_37_1","volume-title":"Mental health and the pandemic: What US surveys have found","author":"Gramlich J","unstructured":"J Gramlich. 2023. Mental health and the pandemic: What US surveys have found. Pew Research Center."},{"key":"e_1_3_2_1_38_1","volume-title":"Safety Under Scaffolding: How Evaluation Conditions Shape Measured Safety. arXiv preprint arXiv:2603.10044","author":"Gringras David","year":"2026","unstructured":"David Gringras. 2026. Safety Under Scaffolding: How Evaluation Conditions Shape Measured Safety. arXiv preprint arXiv:2603.10044 (2026)."},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/3630106.3658959"},{"key":"e_1_3_2_1_40_1","unstructured":"Jiawei Gu Xuhui Jiang Zhichao Shi Hexiang Tan Xuehao Zhai Chengjin Xu Wei Li Yinghan Shen Shengjie Ma Honghao Liu et al. 2024. A survey on llm-as-a-judge. The Innovation (2024)."},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.starsem-1.4"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"crossref","unstructured":"Zhijun Guo Alvina Lai Johan H Thygesen Joseph Farrington Thomas Keen Kezhi Li et al. 2024. Large language models for mental health applications: systematic review. JMIR mental health 11 1 (2024) e57400.","DOI":"10.2196\/57400"},{"key":"e_1_3_2_1_43_1","unstructured":"Anna-Carolina Haensch. 2025. \u201cIt Listens Better Than My Therapist\u201d: Exploring Social Media Discourse on LLMs as Mental Health Tool. arXiv preprint arXiv:2504.12337 (2025)."},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1145\/3715275.3732137"},{"key":"e_1_3_2_1_45_1","volume-title":"Making Sense of the Unsensible: Reflection, Survey, and Challenges for XAI in Large Language Models Toward Human-Centered AI. arXiv preprint arXiv:2505.20305","author":"Herrera Francisco","year":"2025","unstructured":"Francisco Herrera. 2025. Making Sense of the Unsensible: Reflection, Survey, and Challenges for XAI in Large Language Models Toward Human-Centered AI. arXiv preprint arXiv:2505.20305 (2025)."},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.3389\/frai.2025.1609097"},{"key":"e_1_3_2_1_47_1","volume-title":"Proceedings of the 7th International Workshop on Modern Machine Learning Technologies (MoMLeT-2025)","author":"Hota Asutosh","year":"2025","unstructured":"Asutosh Hota and Jussi PP Jokinen. 2025. Conscience conflict? evaluating language models' moral understanding. In Proceedings of the 7th International Workshop on Modern Machine Learning Technologies (MoMLeT-2025), pp.-. CEUR Workshop Proceedings."},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1007\/s40501-025-00363-y"},{"key":"e_1_3_2_1_49_1","volume-title":"Applying and evaluating large language models in mental health care: A scoping review of human-assessed generative tasks. arXiv preprint arXiv:2408.11288","author":"Hua Yining","year":"2024","unstructured":"Yining Hua, Hongbin Na, Zehan Li, Fenglin Liu, Xiao Fang, David Clifton, and John Torous. 2024. Applying and evaluating large language models in mental health care: A scoping review of human-assessed generative tasks. arXiv preprint arXiv:2408.11288 (2024)."},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1145\/3715275.3732014"},{"key":"e_1_3_2_1_51_1","volume-title":"Cognitive behavior therapy: Basics and Beyond","author":"Judith S","unstructured":"S Judith and Beck Beck. 2023. Cognitive behavior therapy: Basics and Beyond. Guilford Press."},{"key":"e_1_3_2_1_52_1","volume-title":"Forty-first International Conference on Machine Learning.","author":"Kambhampati Subbarao","year":"2024","unstructured":"Subbarao Kambhampati, Karthik Valmeekam, Lin Guan, Mudit Verma, Kaya Stechly, Siddhant Bhambri, Lucas Paul Saldyt, and Anil B Murthy. 2024. Position: LLMs can't plan, but can help planning in LLM-modulo frameworks. In Forty-first International Conference on Machine Learning."},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1145\/3711000"},{"key":"e_1_3_2_1_54_1","first-page":"2009","article-title":"Open coding","volume":"23","author":"Khandkar Shahedul Huq","year":"2009","unstructured":"Shahedul Huq Khandkar. 2009. Open coding. University of Calgary 23, 2009 (2009), 2009.","journal-title":"University of Calgary"},{"key":"e_1_3_2_1_55_1","volume-title":"Limitations of large language models in clinical problem-solving arising from inflexible reasoning. Scientific reports 15, 1","author":"Kim Jonathan","year":"2025","unstructured":"Jonathan Kim, Anna Podlasek, Kie Shidara, Feng Liu, Ahmed Alaa, and Danilo Bernardo. 2025. Limitations of large language models in clinical problem-solving arising from inflexible reasoning. Scientific reports 15, 1 (2025), 39426."},{"key":"e_1_3_2_1_56_1","volume-title":"Being Kind Isn't Always Being Safe: Diagnosing Affective Hallucination in LLMs. arXiv preprint arXiv:2508.16921","author":"Kim Sewon","year":"2025","unstructured":"Sewon Kim, Jiwon Kim, Seungwoo Shin, Hyejin Chung, Daeun Moon, Yejin Kwon, and Hyunsoo Yoon. 2025. Being Kind Isn't Always Being Safe: Diagnosing Affective Hallucination in LLMs. arXiv preprint arXiv:2508.16921 (2025)."},{"key":"e_1_3_2_1_57_1","volume-title":"Manipulation and the ai act: Large language model chatbots and the danger of mirrors. arXiv preprint arXiv:2503.18387","author":"Krook Joshua","year":"2025","unstructured":"Joshua Krook. 2025. Manipulation and the ai act: Large language model chatbots and the danger of mirrors. arXiv preprint arXiv:2503.18387 (2025)."},{"key":"e_1_3_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.1080\/01621459.1952.10483441"},{"key":"e_1_3_2_1_59_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2024.3401547"},{"key":"e_1_3_2_1_60_1","doi-asserted-by":"publisher","DOI":"10.1145\/3630106.3658957"},{"key":"e_1_3_2_1_61_1","doi-asserted-by":"publisher","DOI":"10.2196\/59479"},{"key":"e_1_3_2_1_62_1","volume-title":"Jian-Yun Nie, and Ji-Rong Wen.","author":"Li Junyi","year":"2024","unstructured":"Junyi Li, Jie Chen, Ruiyang Ren, Xiaoxue Cheng, Wayne Xin Zhao, Jian-Yun Nie, and Ji-Rong Wen. 2024. The dawn after the dark: An empirical study on factuality hallucination in large language models. arXiv preprint arXiv:2401.03205 (2024)."},{"key":"e_1_3_2_1_63_1","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0908"},{"key":"e_1_3_2_1_64_1","volume-title":"When thinking fails: The pitfalls of reasoning for instruction-following in llms. arXiv preprint arXiv:2505.11423","author":"Li Xiaomin","year":"2025","unstructured":"Xiaomin Li, Zhou Yu, Zhiwei Zhang, Xupeng Chen, Ziji Zhang, Yingying Zhuang, Narayanan Sadagopan, and Anurag Beniwal. 2025. When thinking fails: The pitfalls of reasoning for instruction-following in llms. arXiv preprint arXiv:2505.11423 (2025)."},{"key":"e_1_3_2_1_65_1","volume-title":"A survey on fairness in large language models. arXiv preprint arXiv:2308.10149","author":"Li Yingji","year":"2023","unstructured":"Yingji Li, Mengnan Du, Rui Song, Xin Wang, and Ying Wang. 2023. A survey on fairness in large language models. arXiv preprint arXiv:2308.10149 (2023)."},{"key":"e_1_3_2_1_66_1","volume-title":"Beyond Accuracy: Rethinking Hallucination and Regulatory Response in Generative AI. arXiv preprint arXiv:2509.13345","author":"Li Zihao","year":"2025","unstructured":"Zihao Li, Weiwei Yi, and Jiahong Chen. 2025. Beyond Accuracy: Rethinking Hallucination and Regulatory Response in Generative AI. arXiv preprint arXiv:2509.13345 (2025)."},{"key":"e_1_3_2_1_67_1","volume-title":"Algorithm-Based Clinical Decision Support: Evolving Regulatory Landscape and Best Practices for Local Oversight. Annual Review of Biomedical Data Science 8","author":"Lin Anthony L","year":"2025","unstructured":"Anthony L Lin, Amanda B Parrish, Michael Cary, Christina Silcox, Suresh Balu, J Eric Jelovsek, Cara O'Brien, Michael Pencina, Eric Poon, and Nicoleta J Economou-Zavlanos. 2025. Algorithm-Based Clinical Decision Support: Evolving Regulatory Landscape and Best Practices for Local Oversight. Annual Review of Biomedical Data Science 8 (2025)."},{"key":"e_1_3_2_1_68_1","volume-title":"Ruoxi Jia, et al.","author":"Liu Minqian","year":"2025","unstructured":"Minqian Liu, Zhiyang Xu, Xinyi Zhang, Heajun An, Sarvech Qadir, Qi Zhang, Pamela J Wisniewski, Jin-Hee Cho, Sang Won Lee, Ruoxi Jia, et al. 2025. LLM can be a dangerous persuader: Empirical study of persuasion safety in large language models. arXiv preprint arXiv:2504.10430 (2025)."},{"key":"e_1_3_2_1_69_1","doi-asserted-by":"publisher","DOI":"10.1145\/3711896.3736569"},{"key":"e_1_3_2_1_70_1","volume-title":"Muhammad Faaiz Taufiq, and Hang Li","author":"Liu Yang","year":"2023","unstructured":"Yang Liu, Yuanshun Yao, Jean-Francois Ton, Xiaoying Zhang, Ruocheng Guo, Hao Cheng, Yegor Klochkov, Muhammad Faaiz Taufiq, and Hang Li. 2023. Trustworthy llms: a survey and guideline for evaluating large language models' alignment. arXiv preprint arXiv:2308.05374 (2023)."},{"key":"e_1_3_2_1_71_1","volume-title":"DialogGuard: Multi-Agent Psychosocial Safety Evaluation of Sensitive LLM Responses. arXiv preprint arXiv:2512.02282","author":"Luo Han","year":"2025","unstructured":"Han Luo and Guy Laban. 2025. DialogGuard: Multi-Agent Psychosocial Safety Evaluation of Sensitive LLM Responses. arXiv preprint arXiv:2512.02282 (2025)."},{"key":"e_1_3_2_1_72_1","doi-asserted-by":"publisher","DOI":"10.1145\/3630106.3658932"},{"key":"e_1_3_2_1_73_1","doi-asserted-by":"publisher","DOI":"10.1145\/3630106.3658964"},{"key":"e_1_3_2_1_74_1","doi-asserted-by":"publisher","DOI":"10.1145\/3359174"},{"key":"e_1_3_2_1_75_1","volume-title":"Understanding AI Trustworthiness: A Scoping Review of AIES & FAccT Articles. arXiv preprint arXiv:2510.21293","author":"Mehrotra Siddharth","year":"2025","unstructured":"Siddharth Mehrotra, Jin Huang, Xuelong Fu, Roel Dobbe, Clara I S\u00e1nchez, and Maarten de Rijke. 2025. Understanding AI Trustworthiness: A Scoping Review of AIES & FAccT Articles. arXiv preprint arXiv:2510.21293 (2025)."},{"key":"e_1_3_2_1_76_1","doi-asserted-by":"publisher","DOI":"10.4135\/9798348847807"},{"key":"e_1_3_2_1_77_1","doi-asserted-by":"publisher","DOI":"10.5555\/AAI29756350"},{"key":"e_1_3_2_1_78_1","volume-title":"Victor OK Li, and Lawrence YL Cheung.","author":"Mo Tingyu","year":"2024","unstructured":"Tingyu Mo, Jacqueline CK Lam, Victor OK Li, and Lawrence YL Cheung. 2024. Leveraging large language models for identifying interpretable linguistic markers and enhancing Alzheimer's disease diagnostics. medRxiv (2024), 2024\u201308."},{"key":"e_1_3_2_1_79_1","volume-title":"Efficacy, Challenges, and Future Directions.","author":"Moell Birger","year":"2025","unstructured":"Birger Moell. 2025. The Role of Large Language Models in Clinical Psychology: Current Applications, Efficacy, Challenges, and Future Directions. (2025)."},{"key":"e_1_3_2_1_80_1","doi-asserted-by":"publisher","DOI":"10.2196\/75849"},{"key":"e_1_3_2_1_81_1","doi-asserted-by":"publisher","DOI":"10.1007\/s43681-023-00289-2"},{"key":"e_1_3_2_1_82_1","doi-asserted-by":"publisher","DOI":"10.1176\/appi.focus.20190028"},{"key":"e_1_3_2_1_83_1","doi-asserted-by":"publisher","DOI":"10.1145\/3715275.3732039"},{"key":"e_1_3_2_1_84_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11023-021-09563-w"},{"key":"e_1_3_2_1_85_1","volume-title":"Artificial Empathy: AI based Mental Health. arXiv preprint arXiv:2506.00081","author":"Naik Aditya","year":"2025","unstructured":"Aditya Naik, Jovi Thomas, Teja Sree, and Himavant Reddy. 2025. Artificial Empathy: AI based Mental Health. arXiv preprint arXiv:2506.00081 (2025)."},{"key":"e_1_3_2_1_86_1","unstructured":"Andreas Naoum. 2025. An Empathetic Conversational Agent for Pain Self-Management and Well-Being."},{"key":"e_1_3_2_1_87_1","doi-asserted-by":"crossref","unstructured":"Matthew K Nock Alexander J Millner Eric L Ross Chris J Kennedy Maha Al-Suwaidi Yuval Barak-Corren Victor M Castro Franchesca Castro-Ramirez Tess Lauricella Nicole Murman et al. 2022. Prediction of suicide attempts using clinician assessment patient self-report and electronic health records. JAMA network open 5 1 (2022) e2144373.","DOI":"10.1001\/jamanetworkopen.2021.44373"},{"key":"e_1_3_2_1_88_1","doi-asserted-by":"publisher","DOI":"10.1002\/jclp.22678"},{"key":"e_1_3_2_1_89_1","unstructured":"SL Nowaczyk et al. 2025. Architectures for Building Agentic AI. arXiv preprint arXiv:2512.09458 (2025)."},{"key":"e_1_3_2_1_90_1","volume-title":"Relative informativeness of quantifiers used in syllogistic reasoning. Memory & cognition 30, 1","author":"Oaksford Mike","year":"2002","unstructured":"Mike Oaksford, Lisa Roberts, and Nick Chater. 2002. Relative informativeness of quantifiers used in syllogistic reasoning. Memory & cognition 30, 1 (2002), 138\u2013149."},{"key":"e_1_3_2_1_91_1","volume-title":"World mental health report: Transforming mental health for all","author":"World Health Organization","unstructured":"World Health Organization. 2022. World mental health report: Transforming mental health for all. World Health Organization."},{"key":"e_1_3_2_1_92_1","doi-asserted-by":"publisher","DOI":"10.1145\/3613904.3642934"},{"key":"e_1_3_2_1_93_1","volume-title":"Training LLMs to Recognize Hedges in Spontaneous Narratives. arXiv preprint arXiv:2408.03319","author":"Paige Amie J","year":"2024","unstructured":"Amie J Paige, Adil Soubki, John Murzaku, Owen Rambow, and Susan E Brennan. 2024. Training LLMs to Recognize Hedges in Spontaneous Narratives. arXiv preprint arXiv:2408.03319 (2024)."},{"key":"e_1_3_2_1_94_1","volume-title":"Llm content moderation and user satisfaction: Evidence from response refusals in chatbot arena. Behaviour & Information Technology","author":"Pasch Stefan","year":"2025","unstructured":"Stefan Pasch. 2025. Llm content moderation and user satisfaction: Evidence from response refusals in chatbot arena. Behaviour & Information Technology (2025), 1\u201325."},{"key":"e_1_3_2_1_95_1","first-page":"2001","article-title":"Linguistic inquiry and word count: LIWC 2001. Mahway","volume":"71","author":"Pennebaker James W","year":"2001","unstructured":"James W Pennebaker, Martha E Francis, Roger J Booth, et al. 2001. Linguistic inquiry and word count: LIWC 2001. Mahway: Lawrence Erlbaum Associates 71, 2001 (2001), 2001.","journal-title":"Lawrence Erlbaum Associates"},{"key":"e_1_3_2_1_96_1","doi-asserted-by":"publisher","DOI":"10.2196\/76296"},{"key":"e_1_3_2_1_97_1","doi-asserted-by":"publisher","DOI":"10.1145\/3351095.3372873"},{"key":"e_1_3_2_1_98_1","volume-title":"Ethical reasoning over moral alignment: A case and framework for in-context ethical policies in LLMs. arXiv preprint arXiv:2310.07251","author":"Rao Abhinav","year":"2023","unstructured":"Abhinav Rao, Aditi Khandelwal, Kumar Tanmay, Utkarsh Agarwal, and Monojit Choudhury. 2023. Ethical reasoning over moral alignment: A case and framework for in-context ethical policies in LLMs. arXiv preprint arXiv:2310.07251 (2023)."},{"key":"e_1_3_2_1_99_1","volume-title":"Trism for agentic ai: A review of trust, risk, and security management in llm-based agentic multi-agent systems. arXiv preprint arXiv:2506.04133","author":"Raza Shaina","year":"2025","unstructured":"Shaina Raza, Ranjan Sapkota, Manoj Karkee, and Christos Emmanouilidis. 2025. Trism for agentic ai: A review of trust, risk, and security management in llm-based agentic multi-agent systems. arXiv preprint arXiv:2506.04133 (2025)."},{"key":"e_1_3_2_1_100_1","doi-asserted-by":"publisher","DOI":"10.1002\/wcs.1437"},{"key":"e_1_3_2_1_101_1","volume-title":"Ali Soroush, and Jonathan H Chen.","author":"Savage Thomas","year":"2024","unstructured":"Thomas Savage, John Wang, Robert Gallo, Abdessalem Boukil, Vishwesh Patel, Seyed Amir Ahmad Safavi-Naini, Ali Soroush, and Jonathan H Chen. 2024. Large language model uncertainty measurement and calibration for medical diagnosis and treatment. medRxiv (2024), 2024\u201306."},{"key":"e_1_3_2_1_102_1","doi-asserted-by":"publisher","DOI":"10.2196\/69709"},{"key":"e_1_3_2_1_103_1","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-022-00593-2"},{"key":"e_1_3_2_1_104_1","doi-asserted-by":"publisher","DOI":"10.2196\/52597"},{"key":"e_1_3_2_1_105_1","doi-asserted-by":"publisher","DOI":"10.1038\/s44184-024-00056-z"},{"key":"e_1_3_2_1_106_1","doi-asserted-by":"publisher","DOI":"10.1145\/3442188.3445939"},{"key":"e_1_3_2_1_107_1","volume-title":"Abdallah El Ali, and Jos A Bosch","author":"Sun Xin","year":"2024","unstructured":"Xin Sun, Jan de Wit, Zhuying Li, Jiahuan Pei, Abdallah El Ali, and Jos A Bosch. 2024. Script-Strategy Aligned Generation: Aligning LLMs with Expert-Crafted Dialogue Scripts and Therapeutic Strategies for Psychotherapy. arXiv preprint arXiv 2411.06723 (2024)."},{"key":"e_1_3_2_1_108_1","doi-asserted-by":"publisher","DOI":"10.1177\/0261927X09351676"},{"key":"e_1_3_2_1_109_1","volume-title":"Clinical review of user engagement with mental health smartphone apps: evidence, theory and improvements. Evidence Based Mental Health 21, 3","author":"Torous John","year":"2018","unstructured":"John Torous, Jennifer Nicholas, Mark E Larsen, Joseph Firth, and Helen Christensen. 2018. Clinical review of user engagement with mental health smartphone apps: evidence, theory and improvements. Evidence Based Mental Health 21, 3 (2018)."},{"key":"e_1_3_2_1_110_1","doi-asserted-by":"publisher","DOI":"10.1515\/lass-2024-0018"},{"key":"e_1_3_2_1_111_1","doi-asserted-by":"publisher","DOI":"10.52202\/075280-3275"},{"key":"e_1_3_2_1_112_1","volume-title":"NeurIPS 2022 Foundation Models for Decision Making Workshop.","author":"Valmeekam Karthik","year":"2022","unstructured":"Karthik Valmeekam, Alberto Olmo, Sarath Sreedharan, and Subbarao Kambhampati. 2022. Large language models still can't plan (a benchmark for LLMs on planning and reasoning about change). In NeurIPS 2022 Foundation Models for Decision Making Workshop."},{"key":"e_1_3_2_1_113_1","doi-asserted-by":"crossref","unstructured":"Cheng Wang Yue Liu Baolong Bi Duzhen Zhang Zhong-Zhi Li Yingwei Ma Yufei He Shengju Yu Xinfeng Li Junfeng Fang et al. 2025. Safety in large reasoning models: A survey. arXiv preprint arXiv:2504.17704 (2025).","DOI":"10.18653\/v1\/2025.findings-emnlp.185"},{"key":"e_1_3_2_1_114_1","volume-title":"Bum Chul Kwon, and Jina Huh-Yoo","author":"Wang Lu","year":"2023","unstructured":"Lu Wang, Max Song, Rezvaneh Rezapour, Bum Chul Kwon, and Jina Huh-Yoo. 2023. People's perceptions toward bias and related concepts in large language models: a systematic review. arXiv preprint arXiv:2309.14504 (2023)."},{"key":"e_1_3_2_1_115_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-eacl.61"},{"key":"e_1_3_2_1_116_1","volume-title":"I needed the help. They weren't giving it\u201d: Experiences of young people in tertiary education on waitlists for mental health services in Aotearoa. Ph. D. Dissertation","author":"Wilson-Burke Esta","unstructured":"Esta Wilson-Burke. 2024. \u201cI needed the help. They weren't giving it\u201d: Experiences of young people in tertiary education on waitlists for mental health services in Aotearoa. Ph. D. Dissertation. Open Access Te Herenga Waka-Victoria University of Wellington."},{"key":"e_1_3_2_1_117_1","doi-asserted-by":"publisher","DOI":"10.59231\/edumania\/9010"},{"key":"e_1_3_2_1_118_1","doi-asserted-by":"crossref","unstructured":"Tien Ee Dominic Yeo. 2021. \u201cDo you know how much I suffer?\u201d: How young people negotiate the tellability of their mental health disruption in anonymous distress narratives on social media. Health communication 36 13 (2021) 1606\u20131615.","DOI":"10.1080\/10410236.2020.1775447"},{"key":"e_1_3_2_1_119_1","volume-title":"Rick Siow Mong Goh, and Erik Cambria","author":"Yeo Wei Jie","year":"2024","unstructured":"Wei Jie Yeo, Ranjan Satapathy, Rick Siow Mong Goh, and Erik Cambria. 2024. How interpretable are reasoning explanations from prompting large language models? arXiv preprint arXiv:2402.11863 (2024)."},{"key":"e_1_3_2_1_120_1","doi-asserted-by":"publisher","DOI":"10.1145\/3701041"},{"key":"e_1_3_2_1_121_1","doi-asserted-by":"publisher","DOI":"10.1145\/3658673"}],"event":{"name":"FAccT '26: The 2026 ACM Conference on Fairness, Accountability, and Transparency","location":"Montreal QC Canada","acronym":"FAccT '26","sponsor":["ACM\/SIG"]},"container-title":["Proceedings of the 2026 ACM Conference on Fairness, Accountability, and Transparency"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3805689.3806456","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,29]],"date-time":"2026-06-29T17:56:14Z","timestamp":1782755774000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3805689.3806456"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,25]]},"references-count":121,"alternative-id":["10.1145\/3805689.3806456","10.1145\/3805689"],"URL":"https:\/\/doi.org\/10.1145\/3805689.3806456","relation":{},"subject":[],"published":{"date-parts":[[2026,6,25]]},"assertion":[{"value":"2026-06-25","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}