{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,13]],"date-time":"2026-04-13T19:40:18Z","timestamp":1776109218036,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":96,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,9,28]]},"DOI":"10.1145\/3746059.3747597","type":"proceedings-article","created":{"date-parts":[[2025,9,27]],"date-time":"2025-09-27T07:49:12Z","timestamp":1758959352000},"page":"1-20","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["\"This is My Fault\", Really? Understanding Blind and Low-Vision People\u2019s Perception of Hallucination in Large Vision Language Models"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-8092-4604","authenticated-orcid":false,"given":"Yilin","family":"Tang","sequence":"first","affiliation":[{"name":"Zhejiang University, Hangzhou, Zhejiang, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-5604-5449","authenticated-orcid":false,"given":"Yuyang","family":"Fang","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Zhejiang University, Hangzhou, Zhejiang, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-2125-6024","authenticated-orcid":false,"given":"Tianle","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Digital Media and Design Arts, Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5561-0493","authenticated-orcid":false,"given":"Lingyun","family":"Sun","sequence":"additional","affiliation":[{"name":"International Design Institute, Zhejiang University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9049-0394","authenticated-orcid":false,"given":"Liuqing","family":"Chen","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Zhejiang University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,9,27]]},"reference":[{"key":"e_1_3_3_2_2_2","doi-asserted-by":"publisher","DOI":"10.1145\/3663548.3675631"},{"key":"e_1_3_3_2_3_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1203"},{"key":"e_1_3_3_2_4_2","unstructured":"Aira. 2020. https:\/\/aira.io\/"},{"key":"e_1_3_3_2_5_2","doi-asserted-by":"publisher","DOI":"10.1145\/3663548.3675659"},{"key":"e_1_3_3_2_6_2","doi-asserted-by":"crossref","unstructured":"Robert\u00a0W Andrews J\u00a0Mason Lilly Divya Srivastava and Karen\u00a0M Feigh. 2023. The role of shared mental models in human-AI teams: a theoretical review. Theoretical Issues in Ergonomics Science 24 2 (2023) 129\u2013175.","DOI":"10.1080\/1463922X.2022.2061080"},{"key":"e_1_3_3_2_7_2","unstructured":"Apple. 2020. https:\/\/support.apple.com\/en-hk\/guide\/iphone\/iph3e2e415f\/ios"},{"key":"e_1_3_3_2_8_2","unstructured":"Mohammad\u00a0Reza Armat Abdolghader Assarroudi Mostafa Rad Hassan Sharifi and Abbas Heydari. 2018. Inductive and deductive: Ambiguous labels in qualitative content analysis. The Qualitative Report 23 1 (2018) 219\u2013221."},{"key":"e_1_3_3_2_9_2","unstructured":"Yujin Baek ChaeHun Park Jaeseok Kim Yu-Jung Heo Du-Seong Chang and Jaegul Choo. 2024. Evaluating visual and cultural interpretation: The k-viscuit benchmark with human-vlm collaboration. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2406.16469 (2024)."},{"key":"e_1_3_3_2_10_2","doi-asserted-by":"publisher","unstructured":"Zechen Bai Pichao Wang Tianjun Xiao Tong He Zongbo Han Zheng Zhang and Mike\u00a0Zheng Shou. 2024. Hallucination of multimodal large language models: A survey. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2404.18930 (2024). 10.48550\/arXiv.2404.18930","DOI":"10.48550\/arXiv.2404.18930"},{"key":"e_1_3_3_2_11_2","doi-asserted-by":"publisher","DOI":"10.1609\/hcomp.v7i1.5285"},{"key":"e_1_3_3_2_12_2","volume-title":"Contextual Design: Defining Customer-Centered Systems","author":"Beyer Hugh","year":"1997","unstructured":"Hugh Beyer and Karen Holtzblatt. 1997. Contextual Design: Defining Customer-Centered Systems. Vol.\u00a06. Morgan Kaufmann Publishers Inc., San Francisco, CA, USA. 32\u201342 pages."},{"key":"e_1_3_3_2_13_2","doi-asserted-by":"publisher","DOI":"10.1145\/1866029.1866080"},{"key":"e_1_3_3_2_14_2","volume-title":"Natural language processing with Python: analyzing text with the natural language toolkit","author":"Bird Steven","year":"2009","unstructured":"Steven Bird, Ewan Klein, and Edward Loper. 2009. Natural language processing with Python: analyzing text with the natural language toolkit. \" O\u2019Reilly Media, Inc.\"."},{"key":"e_1_3_3_2_15_2","doi-asserted-by":"publisher","unstructured":"Ali Borji. 2023. A categorical archive of chatgpt failures. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2302.03494 (2023). 10.48550\/arXiv.2302.03494","DOI":"10.48550\/arXiv.2302.03494"},{"key":"e_1_3_3_2_16_2","doi-asserted-by":"publisher","DOI":"10.1145\/3240925.3240981"},{"key":"e_1_3_3_2_17_2","unstructured":"ByteDance. 2024. https:\/\/www.doubao.com\/"},{"key":"e_1_3_3_2_18_2","doi-asserted-by":"publisher","DOI":"10.1145\/3654777.3676375"},{"key":"e_1_3_3_2_19_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01405"},{"key":"e_1_3_3_2_20_2","series-title":"Proceedings of Machine Learning Research","first-page":"7824","volume-title":"Proceedings of the 41st International Conference on Machine Learning","volume":"235","author":"Chen Zhaorun","year":"2024","unstructured":"Zhaorun Chen, Zhuokai Zhao, Hongyin Luo, Huaxiu Yao, Bo Li, and Jiawei Zhou. 2024. HALC: Object Hallucination Reduction via Adaptive Focal-Contrast Decoding. In Proceedings of the 41st International Conference on Machine Learning(Proceedings of Machine Learning Research, Vol.\u00a0235), Ruslan Salakhutdinov, Zico Kolter, Katherine Heller, Adrian Weller, Nuria Oliver, Jonathan Scarlett, and Felix Berkenkamp (Eds.). PMLR, 7824\u20137846. https:\/\/proceedings.mlr.press\/v235\/chen24bi.html"},{"key":"e_1_3_3_2_21_2","doi-asserted-by":"publisher","DOI":"10.1145\/3613904.3641904"},{"key":"e_1_3_3_2_22_2","series-title":"(ICML\u201924)","volume-title":"Proceedings of the 41st International Conference on Machine Learning","author":"Chiang Wei-Lin","year":"2024","unstructured":"Wei-Lin Chiang, Lianmin Zheng, Ying Sheng, Anastasios\u00a0N. Angelopoulos, Tianle Li, Dacheng Li, Banghua Zhu, Hao Zhang, Michael\u00a0I. Jordan, Joseph\u00a0E. Gonzalez, and Ion Stoica. 2024. Chatbot arena: an open platform for evaluating LLMs by human preference. In Proceedings of the 41st International Conference on Machine Learning (Vienna, Austria) (ICML\u201924). JMLR.org, Article 331, 30\u00a0pages."},{"key":"e_1_3_3_2_23_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00370"},{"key":"e_1_3_3_2_24_2","unstructured":"Baidu\u00a0Smart Cloud. 2022. https:\/\/cloud.baidu.com\/"},{"key":"e_1_3_3_2_25_2","doi-asserted-by":"publisher","DOI":"10.1145\/3597638.3608386"},{"key":"e_1_3_3_2_26_2","first-page":"49250","volume-title":"Advances in Neural Information Processing Systems","volume":"36","author":"Dai Wenliang","year":"2023","unstructured":"Wenliang Dai, Junnan Li, DONGXU LI, Anthony Tiong, Junqi Zhao, Weisheng Wang, Boyang Li, Pascale\u00a0N Fung, and Steven Hoi. 2023. InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning. In Advances in Neural Information Processing Systems , A.\u00a0Oh, T.\u00a0Naumann, A.\u00a0Globerson, K.\u00a0Saenko, M.\u00a0Hardt, and S.\u00a0Levine (Eds.), Vol.\u00a036. Curran Associates, Inc., 49250\u201349267. https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2023\/file\/9a6a435e75419a836fe47ab6793623e6-Paper-Conference.pdf"},{"key":"e_1_3_3_2_27_2","unstructured":"Be\u00a0My Eyes. 2015. https:\/\/www.bemyeyes.com\/"},{"key":"e_1_3_3_2_28_2","unstructured":"Be\u00a0My Eyes. 2023. Introducing Be My AI(formerly virtual volunteer) for People who are blind or have low vision powered by OpenAI\u2019s GPT-4. https:\/\/www.bemyeyes.com\/blog\/introducing-be-my-eyes-virtual-volunteer"},{"key":"e_1_3_3_2_29_2","first-page":"2065","volume-title":"33rd USENIX Security Symposium (USENIX Security 24)","author":"Feng Yuanyuan","year":"2024","unstructured":"Yuanyuan Feng, Abhilasha Ravichander, Yaxing Yao, Shikun Zhang, and Rex Chen. 2024. Understanding How to Inform Blind and { Low-Vision} Users about Data Privacy through Privacy Question Answering Assistants. In 33rd USENIX Security Symposium (USENIX Security 24). 2065\u20132082."},{"key":"e_1_3_3_2_30_2","doi-asserted-by":"publisher","DOI":"10.1145\/3597638.3608955"},{"key":"e_1_3_3_2_31_2","doi-asserted-by":"publisher","unstructured":"Sreyan Ghosh Chandra Kiran\u00a0Reddy Evuru Sonal Kumar Utkarsh Tyagi Oriol Nieto Zeyu Jin and Dinesh Manocha. 2024. VDGD: Mitigating LVLM Hallucinations in Cognitive Prompts by Bridging the Visual Perception Gap. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2405.15683 (2024). 10.48550\/arXiv.2405.15683","DOI":"10.48550\/arXiv.2405.15683"},{"key":"e_1_3_3_2_32_2","doi-asserted-by":"publisher","DOI":"10.1145\/3613904.3642211"},{"key":"e_1_3_3_2_33_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i16.29771"},{"key":"e_1_3_3_2_34_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00380"},{"key":"e_1_3_3_2_35_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58520-4_25"},{"key":"e_1_3_3_2_36_2","doi-asserted-by":"publisher","unstructured":"Lei Huang Weijiang Yu Weitao Ma Weihong Zhong Zhangyin Feng Haotian Wang Qianglong Chen Weihua Peng Xiaocheng Feng Bing Qin and Ting Liu. 2025. A Survey on Hallucination in Large Language Models: Principles Taxonomy Challenges and Open Questions. ACM Trans. Inf. Syst. 43 2 Article 42 (Jan. 2025) 55\u00a0pages. 10.1145\/3703155","DOI":"10.1145\/3703155"},{"key":"e_1_3_3_2_37_2","doi-asserted-by":"crossref","unstructured":"Lei Huang Weijiang Yu Weitao Ma Weihong Zhong Zhangyin Feng Haotian Wang Qianglong Chen Weihua Peng Xiaocheng Feng Bing Qin and Ting Liu. 2025. A survey on hallucination in large language models: Principles taxonomy challenges and open questions. ACM Transactions on Information Systems 43 2 (2025) 1\u201355.","DOI":"10.1145\/3703155"},{"key":"e_1_3_3_2_38_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00686"},{"key":"e_1_3_3_2_39_2","doi-asserted-by":"publisher","DOI":"10.1145\/3706599.3719785"},{"key":"e_1_3_3_2_40_2","doi-asserted-by":"publisher","DOI":"10.1145\/3586183.3606735"},{"key":"e_1_3_3_2_41_2","volume-title":"Workshop on Demographic Diversity in Computer Vision@ CVPR 2025","author":"Huh Mina","year":"2024","unstructured":"Mina Huh, Fangyuan Xu, Yi-Hao Peng, Chongyan Chen, Danna Gurari, Eunsol Choi, and Amy Pavel. 2024. Long-form answers to visual questions from blind and low vision people. In Workshop on Demographic Diversity in Computer Vision@ CVPR 2025."},{"key":"e_1_3_3_2_42_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICAA58325.2023.00029"},{"key":"e_1_3_3_2_43_2","doi-asserted-by":"publisher","unstructured":"Chaoya Jiang Hongrui Jia Mengfan Dong Wei Ye Haiyang Xu Ming Yan Ji Zhang and Shikun Zhang. 2024. Hal-Eval: A Universal and Fine-grained Hallucination Evaluation Framework for Large Vision Language Models. (2024) 525\u2013534. 10.1145\/3664647.3680576","DOI":"10.1145\/3664647.3680576"},{"key":"e_1_3_3_2_44_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-emnlp.290"},{"key":"e_1_3_3_2_45_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02571"},{"key":"e_1_3_3_2_46_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-emnlp.626"},{"key":"e_1_3_3_2_47_2","unstructured":"Elizabeth Kupferstein Yuhang Zhao Shiri Azenkot and Hathaitorn Rojnirun. 2020. Understanding the use of artificial intelligence based visual aids for people with visual impairments. Investigative Ophthalmology & Visual Science 61 7 (2020) 932\u2013932."},{"key":"e_1_3_3_2_48_2","doi-asserted-by":"publisher","DOI":"10.1145\/3613904.3642116"},{"key":"e_1_3_3_2_49_2","doi-asserted-by":"publisher","DOI":"10.1145\/3491102.3501966"},{"key":"e_1_3_3_2_50_2","doi-asserted-by":"publisher","DOI":"10.1145\/3603555.3603565"},{"key":"e_1_3_3_2_51_2","doi-asserted-by":"publisher","DOI":"10.1145\/3613904.3642428"},{"key":"e_1_3_3_2_52_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01316"},{"key":"e_1_3_3_2_53_2","unstructured":"Cheng Li Mengzhuo Chen Jindong Wang Sunayana Sitaram and Xing Xie. 2024. Culturellm: Incorporating cultural differences into large language models. Advances in Neural Information Processing Systems 37 (2024) 84799\u201384838."},{"key":"e_1_3_3_2_54_2","volume-title":"Mandarin Chinese: A functional reference grammar","author":"Li Charles\u00a0N","year":"1989","unstructured":"Charles\u00a0N Li and Sandra\u00a0A Thompson. 1989. Mandarin Chinese: A functional reference grammar. Univ of California Press."},{"key":"e_1_3_3_2_55_2","doi-asserted-by":"publisher","unstructured":"Xingxuan Li Ruochen Zhao Yew\u00a0Ken Chia Bosheng Ding Lidong Bing Shafiq Joty and Soujanya Poria. 2023. Chain of knowledge: A framework for grounding large language models with structured knowledge bases. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2305.13269 3 (2023). 10.48550\/arXiv.2305.13269","DOI":"10.48550\/arXiv.2305.13269"},{"key":"e_1_3_3_2_56_2","unstructured":"Q.\u00a0Vera Liao and Jennifer\u00a0Wortman Vaughan. 2023. AI Transparency in the Age of LLMs: A Human-Centered Research Roadmap. arxiv:https:\/\/arXiv.org\/abs\/2306.01941\u00a0[cs.HC] https:\/\/arxiv.org\/abs\/2306.01941"},{"key":"e_1_3_3_2_57_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"e_1_3_3_2_58_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"e_1_3_3_2_59_2","doi-asserted-by":"publisher","unstructured":"Hanchao Liu Wenyuan Xue Yifei Chen Dapeng Chen Xiutian Zhao Ke Wang Liping Hou Rongjun Li and Wei Peng. 2024. A survey on hallucination in large vision-language models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2402.00253 (2024). 10.48550\/arXiv.2402.00253","DOI":"10.48550\/arXiv.2402.00253"},{"key":"e_1_3_3_2_60_2","doi-asserted-by":"publisher","unstructured":"Jiazhen Liu Yuhan Fu Ruobing Xie Runquan Xie Xingwu Sun Fengzong Lian Zhanhui Kang and Xirong Li. 2024. PhD: A prompted visual hallucination evaluation dataset. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2403.11116 (2024). 10.48550\/arXiv.2403.11116","DOI":"10.48550\/arXiv.2403.11116"},{"key":"e_1_3_3_2_61_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.alvr-1.4"},{"key":"e_1_3_3_2_62_2","doi-asserted-by":"publisher","DOI":"10.1145\/3025453.3025814"},{"key":"e_1_3_3_2_63_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.10475"},{"key":"e_1_3_3_2_64_2","unstructured":"Abhika Mishra Akari Asai Vidhisha Balachandran Yizhong Wang Graham Neubig Yulia Tsvetkov and Hannaneh Hajishirzi. 2024. Fine-grained Hallucination Detection and Editing for Language Models. arxiv:https:\/\/arXiv.org\/abs\/2401.06855\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/2401.06855"},{"key":"e_1_3_3_2_65_2","doi-asserted-by":"crossref","unstructured":"Alicia O\u2019Cathain and Kate Thomas. 2006. Combining qualitative and quantitative methods. Qualitative research in health care (2006) 102\u2013111.","DOI":"10.1002\/9780470750841.ch9"},{"key":"e_1_3_3_2_66_2","unstructured":"OpenAI. 2023. Be My Eyes uses GPT-4 to transform visual accessibility.https:\/\/openai.com\/index\/be-my-eyes\/"},{"key":"e_1_3_3_2_67_2","unstructured":"OpenAI. 2024. https:\/\/openai.com\/index\/hello-gpt-4o\/"},{"key":"e_1_3_3_2_68_2","doi-asserted-by":"publisher","DOI":"10.1109\/IC3IOT53935.2022.9767967"},{"key":"e_1_3_3_2_69_2","doi-asserted-by":"publisher","DOI":"10.1145\/3531146.3533158"},{"key":"e_1_3_3_2_70_2","unstructured":"Vipula Rawte Anku Rani Harshad Sharma Neeraj Anand Krishnav Rajbangshi Amit Sheth and Amitava Das. 2024. Visual hallucination: Definition quantification and prescriptive remediations. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2403.17306 (2024)."},{"key":"e_1_3_3_2_71_2","doi-asserted-by":"publisher","unstructured":"Vipula Rawte Amit Sheth and Amitava Das. 2023. A survey of hallucination in large foundation models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2309.05922 (2023). 10.48550\/arXiv.2309.05922","DOI":"10.48550\/arXiv.2309.05922"},{"key":"e_1_3_3_2_72_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1437"},{"key":"e_1_3_3_2_73_2","doi-asserted-by":"crossref","unstructured":"Muhammad Rabani\u00a0Mohd Romlay Siti\u00a0Fauziah Toha Azhar\u00a0Mohd Ibrahim and Ibrahim Venkat. 2021. Methodologies and evaluation of electronic travel aids for the visually impaired people: a review. Bulletin of Electrical Engineering and Informatics 10 3 (2021) 1747\u20131758.","DOI":"10.11591\/eei.v10i3.3055"},{"key":"e_1_3_3_2_74_2","volume-title":"CHI 2019 Workshop: Where is the human? Bridging the gap between AI and HCI","author":"Rutjes Heleen","year":"2019","unstructured":"Heleen Rutjes, Martijn Willemsen, and Wijnand IJsselsteijn. 2019. Considerations on explainable AI and users\u2019 mental models. In CHI 2019 Workshop: Where is the human? Bridging the gap between AI and HCI. Association for Computing Machinery, Inc."},{"key":"e_1_3_3_2_75_2","doi-asserted-by":"publisher","unstructured":"Pritam Sarkar Sayna Ebrahimi Ali Etemad Ahmad Beirami Sercan\u00a0\u00d6 Ar\u0131k and Tomas Pfister. 2024. Mitigating Object Hallucination via Data Augmented Contrastive Tuning. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2405.18654 (2024). 10.48550\/arXiv.2405.18654","DOI":"10.48550\/arXiv.2405.18654"},{"key":"e_1_3_3_2_76_2","doi-asserted-by":"crossref","unstructured":"Abigale Stangl Kristina Shiroma Nathan Davis Bo Xie Kenneth\u00a0R Fleischmann Leah Findlater and Danna Gurari. 2022. Privacy concerns for visual assistance technologies. ACM Transactions on Accessible Computing (TACCESS) 15 2 (2022) 1\u201343.","DOI":"10.1145\/3517384"},{"key":"e_1_3_3_2_77_2","doi-asserted-by":"publisher","DOI":"10.1145\/3373625.3417014"},{"key":"e_1_3_3_2_78_2","doi-asserted-by":"crossref","unstructured":"Yujie Sun Dongfang Sheng Zihan Zhou and Yifei Wu. 2024. AI hallucination: towards a comprehensive classification of distorted information in artificial intelligence-generated content. Humanities and Social Sciences Communications 11 1 (2024) 1\u201314.","DOI":"10.1057\/s41599-024-03811-x"},{"key":"e_1_3_3_2_79_2","doi-asserted-by":"publisher","DOI":"10.1145\/3706598.3713433"},{"key":"e_1_3_3_2_80_2","doi-asserted-by":"publisher","DOI":"10.1145\/3544548.3580933"},{"key":"e_1_3_3_2_81_2","doi-asserted-by":"publisher","unstructured":"Junyang Wang Yiyang Zhou Guohai Xu Pengcheng Shi Chenlin Zhao Haiyang Xu Qinghao Ye Ming Yan Ji Zhang Jihua Zhu Jitao Sang and Haoyu Tang. 2023. Evaluation and analysis of hallucination in large vision-language models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2308.15126 (2023). 10.48550\/arXiv.2308.15126","DOI":"10.48550\/arXiv.2308.15126"},{"key":"e_1_3_3_2_82_2","unstructured":"Junyang Wang Yiyang Zhou Guohai Xu Pengcheng Shi Chenlin Zhao Haiyang Xu Qinghao Ye Ming Yan Ji Zhang Jihua Zhu Jitao Sang and Haoyu Tang. 2023. Evaluation and Analysis of Hallucination in Large Vision-Language Models. arxiv:https:\/\/arXiv.org\/abs\/2308.15126\u00a0[cs.LG] https:\/\/arxiv.org\/abs\/2308.15126"},{"key":"e_1_3_3_2_83_2","doi-asserted-by":"crossref","unstructured":"Min Wang and Dan Wu. 2021. ICT-based assistive technology as the extension of human eyes: technological empowerment and social inclusion of visually impaired people in China. Asian Journal of Communication 31 6 (2021) 470\u2013484.","DOI":"10.1080\/01292986.2021.1913619"},{"key":"e_1_3_3_2_84_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.937"},{"key":"e_1_3_3_2_85_2","unstructured":"Michael Williams and Tami Moser. 2019. The Art of Coding and Thematic Exploration in Qualitative Research. International Management Review 15 1 (2019) 45\u201355. https:\/\/api.semanticscholar.org\/CorpusID:198662452"},{"key":"e_1_3_3_2_86_2","series-title":"Proceedings of Machine Learning Research","first-page":"53553","volume-title":"Proceedings of the 41st International Conference on Machine Learning","volume":"235","author":"Wu Mingrui","year":"2024","unstructured":"Mingrui Wu, Jiayi Ji, Oucheng Huang, Jiale Li, Yuhang Wu, Xiaoshuai Sun, and Rongrong Ji. 2024. Evaluating and Analyzing Relationship Hallucinations in Large Vision-Language Models. In Proceedings of the 41st International Conference on Machine Learning(Proceedings of Machine Learning Research, Vol.\u00a0235), Ruslan Salakhutdinov, Zico Kolter, Katherine Heller, Adrian Weller, Nuria Oliver, Jonathan Scarlett, and Felix Berkenkamp (Eds.). PMLR, 53553\u201353570. https:\/\/proceedings.mlr.press\/v235\/wu24l.html"},{"key":"e_1_3_3_2_87_2","doi-asserted-by":"publisher","DOI":"10.1145\/2998181.2998364"},{"key":"e_1_3_3_2_88_2","doi-asserted-by":"publisher","unstructured":"Ziwei Xu Sanjay Jain and Mohan Kankanhalli. 2024. Hallucination is inevitable: An innate limitation of large language models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2401.11817 (2024). 10.48550\/arXiv.2401.11817","DOI":"10.48550\/arXiv.2401.11817"},{"key":"e_1_3_3_2_89_2","doi-asserted-by":"publisher","unstructured":"Bei Yan Jie Zhang Zheng Yuan Shiguang Shan and Xilin Chen. 2024. Evaluating the Quality of Hallucination Benchmarks for Large Vision-Language Models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2406.17115 (2024). 10.48550\/arXiv.2406.17115","DOI":"10.48550\/arXiv.2406.17115"},{"key":"e_1_3_3_2_90_2","doi-asserted-by":"crossref","unstructured":"Xiaoyu Zeng Yanan Wang Tai-Yin Chiu Nilavra Bhattacharya and Danna Gurari. 2020. Vision skills needed to answer visual questions. Proceedings of the ACM on Human-Computer Interaction 4 CSCW2 (2020) 1\u201331.","DOI":"10.1145\/3415220"},{"key":"e_1_3_3_2_91_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.121"},{"key":"e_1_3_3_2_92_2","first-page":"1","volume-title":"Proceedings of the CHI Conference on Human Factors in Computing Systems","author":"Zhang Zhiping","year":"2024","unstructured":"Zhiping Zhang, Michelle Jia, Hao-Ping Lee, Bingsheng Yao, Sauvik Das, Ada Lerner, Dakuo Wang, and Tianshi Li. 2024. \"It\u2019s a Fair Game\", or Is It? Examining How Users Navigate Disclosure Risks and Benefits When Using LLM-Based Conversational Agents. In Proceedings of the CHI Conference on Human Factors in Computing Systems. 1\u201326."},{"key":"e_1_3_3_2_93_2","doi-asserted-by":"publisher","unstructured":"Linxi Zhao Yihe Deng Weitong Zhang and Quanquan Gu. 2024. Mitigating object hallucination in large vision-language models via classifier-free guidance. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2402.08680 (2024). 10.48550\/arXiv.2402.08680","DOI":"10.48550\/arXiv.2402.08680"},{"key":"e_1_3_3_2_94_2","doi-asserted-by":"publisher","unstructured":"Yi Zhao Yilin Zhang Rong Xiang Jing Li and Hillming Li. 2024. VIALM: A survey and benchmark of visually impaired assistance with large models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2402.01735 (2024). 10.48550\/arXiv.2402.01735","DOI":"10.48550\/arXiv.2402.01735"},{"key":"e_1_3_3_2_95_2","unstructured":"ZhipuAI. 2024. https:\/\/chatglm.cn\/"},{"key":"e_1_3_3_2_96_2","unstructured":"Qishuai Zhong Yike Yun and Aixin Sun. 2024. Cultural value differences of LLMs: Prompt language and model size. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2407.16891 (2024)."},{"key":"e_1_3_3_2_97_2","unstructured":"Yiyang Zhou Chenhang Cui Jaehong Yoon Linjun Zhang Zhun Deng Chelsea Finn Mohit Bansal and Huaxiu Yao. 2024. Analyzing and mitigating object hallucination in large vision-language models. Publisher Copyright: \u00a9 2024 12th International Conference on Learning Representations ICLR 2024. All rights reserved.; 12th International Conference on Learning Representations ICLR 2024 ; Conference date: 07-05-2024 Through 11-05-2024."}],"event":{"name":"UIST '25: The 38th Annual ACM Symposium on User Interface Software and Technology","location":"Busan Republic of Korea","acronym":"UIST '25","sponsor":["SIGCHI ACM Special Interest Group on Computer-Human Interaction","SIGGRAPH ACM Special Interest Group on Computer Graphics and Interactive Techniques"]},"container-title":["Proceedings of the 38th Annual ACM Symposium on User Interface Software and Technology"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3746059.3747597","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,27]],"date-time":"2025-09-27T22:03:52Z","timestamp":1759010632000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746059.3747597"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,27]]},"references-count":96,"alternative-id":["10.1145\/3746059.3747597","10.1145\/3746059"],"URL":"https:\/\/doi.org\/10.1145\/3746059.3747597","relation":{},"subject":[],"published":{"date-parts":[[2025,9,27]]},"assertion":[{"value":"2025-09-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}