CoChat

How Multimodal Large Language Models Support Access to Visual Information: A Diary Study With Blind and Low Vision People

Gonzalez Penuela, Ricardo E., Jung, Crescentia, Lin, Sharon, Hu, Ruiying, Azenkot, Shiri · 2026 · Proceedings of the 2026 CHI Conference on Human Factors in Computing Systems
Cited by 6

The DOI matches its Crossref record; 10 of the 10 references it cites were found in a registry or an index.

Overview

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1145/3772318.3793266

Cites

10 of 10 references verified0 citation errors · 0 not checkable

Statistics

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Research works printed but not linked: 64

  1. 10.1145/3663548.3675659 · DOI · Paper page
  2. Peter Anderson Basura Fernando Mark Johnson and Stephen Gould. 2016. SPICE: Semantic Propositional Image Caption Evaluation. arxiv:https://arXiv.org/abs/1607.08822 [cs.CV] · DOI · Paper page
  3. Hammad A. Ayyubi Md. Mehrab Tanjim Julian J. McAuley and Garrison W. Cottrell. 2020. Generating Rationales in Visual Question Answering. arxiv:https://arXiv.org/abs/2004.02032 [cs.AI] https://arxiv.org/abs/2004.02032 · arXiv
  4. 10.1145/1866029.1866080 · DOI · Paper page
  5. 10.1109/CVPRW.2010.5543821 · DOI · Paper page
  6. Erin Brady. 2015. Using social microvolunteering to answer visual questions from blind users. 4 pages. 10.1145/2809904.2809910 · DOI
  7. Erin Brady Meredith Morris and Jeffrey Bigham. 2014. Friendsourcing for the Greater Good: Perceptions of Social Microvolunteering. Proceedings of the AAAI Conference on Human Computation and Crowdsourcing 2 1 (Sep. 2014) 6–7. 10.1609/hcomp.v2i1.13174 · doi:10.1609/hcomp.v2i1.13174
  8. 10.1145/2470654.2481291 · DOI · Paper page
  9. 10.1145/2441776.2441915 · DOI · Paper page
  10. 10.1007/978-3-031-92089-9_22 · DOI
  11. 10.1109/HSI.2008.4581561 · DOI
  12. 10.1145/2384916.2384941 · DOI · Paper page
  13. Kilian Carolan Laura Fennelly and Alan F. Smeaton. 2024. A Review of Multi-Modal Large Language and Vision Models. arxiv:https://arXiv.org/abs/2404.01322 [cs.CL] https://arxiv.org/abs/2404.01322 · arXiv
  14. 10.1145/3654777.3676375 · DOI
  15. 10.1145/3663547.3746319 · DOI
  16. 10.1007/978-3-319-49655-9_2 · DOI
  17. 10.1007/978-3-031-73195-2_15 · DOI
  18. Lin Chen Jinsong Li Xiaoyi Dong Pan Zhang Conghui He Jiaqi Wang Feng Zhao and Dahua Lin. 2023. ShareGPT4V: Improving Large Multi-Modal Models with Better Captions. arxiv:https://arXiv.org/abs/2311.12793 [cs.CV] https://arxiv.org/abs/2311.12793 · arXiv
  19. 10.1145/3663547.3746393 · DOI · Paper page
  20. Kanzhi Cheng Wenpo Song Jiaxin Fan Zheng Ma Qiushi Sun Fangzhi Xu Chenyang Yan Nuo Chen Jianbing Zhang and Jiajun Chen. 2025. CapArena: Benchmarking and Analyzing Detailed Image Captioning in the LLM Era. arxiv:https://arXiv.org/abs/2503.12329 [cs.CV] https://arxiv.org/abs/2503.12329 · arXiv
  21. Ben Cottier Robi Rahman Loredana Fattorini Nestor Maslej Tamay Besiroglu and David Owen. 2025. The rising costs of training frontier AI models. arxiv:https://arXiv.org/abs/2405.21015 [cs.CY] https://arxiv.org/abs/2405.21015 · arXiv
  22. 10.1145/3613904.3642325 · DOI · Paper page
  23. Vanja Garaj Rommanee Jirawimut Piotr Ptasinski Franjo Cecelja and Wamadeva Balachandran. 2003. A system for remote sighted guidance of visually impaired pedestrians. British Journal of Visual Impairment 21 2 (2003) 55–63. · DOI
  24. 10.1145/2982142.2982200 · DOI
  25. 10.1145/3613904.3642211 · DOI · Paper page
  26. Christina Granquist Susan Y Sun Sandra R Montezuma Tu M Tran Rachel Gage and Gordon E Legge. 2021. Evaluation and comparison of artificial intelligence vision aids: Orcam myeye 1 and seeing ai. Journal of Visual Impairment & Blindness 115 4 (2021) 277–285. · DOI · Paper page
  27. 10.1145/3663548.3675658 · DOI · Paper page
  28. Rex Hartson and Pardha S Pyla. 2012. The UX Book: Process and guidelines for ensuring a quality user experience. Morgan Kaufmann, San Diego, CA.
  29. 10.1145/3663548.3675635 · DOI · Paper page
  30. Mina Huh Fangyuan Xu Yi-Hao Peng Chongyan Chen Hansika Murugu Danna Gurari Eunsol Choi and Amy Pavel. 2024. Long-Form Answers to Visual Questions from Blind and Low Vision People. arxiv:https://arXiv.org/abs/2408.06303 [cs.CL] https://arxiv.org/abs/2408.06303 · arXiv
  31. Ziad Hunaiti Vanja Garaj and Wamadeva Balachandran. 2006. A remote vision guidance system for visually impaired pedestrians. The journal of navigation 59 3 (2006) 497–504. · DOI
  32. Adam Tauman Kalai Ofir Nachum Santosh S. Vempala and Edwin Zhang. 2025. Why Language Models Hallucinate. arxiv:https://arXiv.org/abs/2509.04664 [cs.CL] https://arxiv.org/abs/2509.04664 · arXiv
  33. 10.1145/3677846.3677860 · DOI
  34. 10.1145/3313831.3376823 · DOI · Paper page
  35. 10.1145/3544548.3581337 · DOI
  36. 10.1145/3517428.3544826 · DOI
  37. 10.1109/ICCE63647.2025.10929822 · doi:10.1109/icce63647.2025.10929822
  38. 10.1145/2513383.2517033 · DOI · Paper page
  39. 10.3115/1626355.1626389 · DOI · Paper page
  40. 10.1145/3441852.3476548 · DOI · Paper page
  41. Sooyeon Lee Madison Reddie Krish Gurdasani Xiying Wang Jordan Beck Mary Beth Rosson and John M. Carroll. 2018. Conversations for Vision: Remote Sighted Assistants Helping People with Visual Impairments. arxiv:https://arXiv.org/abs/1812.00148 [cs.HC] https://arxiv.org/abs/1812.00148 · arXiv
  42. 10.1145/3313831.3376591 · DOI · Paper page
  43. Saehyung Lee Seunghyun Yoon Trung Bui Jing Shi and Sungroh Yoon. 2025. Toward Robust Hyper-Detailed Image Captioning: A Multiagent Approach and Dual Evaluation Metrics for Factuality and Coverage. arxiv:https://arXiv.org/abs/2412.15484 [cs.CV] https://arxiv.org/abs/2412.15484 · arXiv
  44. 10.1145/3490099.3511113 · DOI · Paper page
  45. 10.1145/3613904.3642233 · DOI
  46. 10.1145/3663548.3675662 · DOI
  47. Kun Li George Vosselman and Michael Ying Yang. 2025. Multimodal Rationales for Explainable Visual Question Answering. arxiv:https://arXiv.org/abs/2402.03896 [cs.CV] https://arxiv.org/abs/2402.03896 · arXiv
  48. Chin-Yew Lin. 2004. ROUGE: A Package for Automatic Evaluation of Summaries. In Text Summarization Branches Out. Association for Computational Linguistics, Barcelona, Spain, 74–81. https://aclanthology.org/W04-1013/
  49. 10.1145/3706598.3713486 · DOI
  50. Brian J Nguyen William S Chen Allison J Chen Andrew Utt Emily Hill Ryan Apgar and Daniel L Chao. 2019. Large-scale assessment of needs in low vision individuals using the Aira assistive technology. Clinical Ophthalmology 13 (2019) 1853–1868. 10.2147/OPTH.S215658 · DOI
  51. 10.3115/1073083.1073135 · DOI · Paper page
  52. Johnny Saldaña. 2021. The Coding Manual for Qualitative Researchers (4th ed.). SAGE Publications Limited, Thousand Oaks, CA.
  53. 10.1145/3663547.3746335 · DOI
  54. Ramakrishna Vedantam C. Lawrence Zitnick and Devi Parikh. 2015. CIDEr: Consensus-based Image Description Evaluation. arxiv:https://arXiv.org/abs/1411.5726 [cs.CV] https://arxiv.org/abs/1411.5726 · arXiv
  55. Jingyi Xie Madison Reddie Sooyeon Lee Syed Masum Billah Zihan Zhou Chun-Hua Tsai and John M Carroll. 2022. Iterative design and prototyping of computer vision mediated remote sighted assistance. ACM Transactions on Computer-Human Interaction (TOCHI) 29 4 (2022) 1–40. · DOI
  56. 10.1145/3563657.3596019 · DOI
  57. 10.1145/3532106.3533560 · DOI
  58. 10.1145/3706598.3714210 · DOI · Paper page
  59. 10.1145/3613904.3642030 · DOI
  60. Jingyi Xie Rui Yu He Zhang Sooyeon Lee Syed Masum Billah and John M. Carroll. 2024. Emerging Practices for Large Multimodal Model (LMM) Assistance for People with Visual Impairments: Implications for Design. arxiv:https://arXiv.org/abs/2407.08882 [cs.HC] https://arxiv.org/abs/2407.08882 · arXiv
  61. Zhengyuan Yang Linjie Li Kevin Lin Jianfeng Wang Chung-Ching Lin Zicheng Liu and Lijuan Wang. 2023. The dawn of lmms: Preliminary explorations with gpt-4v (ision). arXiv preprint arXiv:https://arXiv.org/abs/2309.17421 9 1 (2023) 1. · arXiv
  62. Rui Yu Sooyeon Lee Jingyi Xie Syed Masum Billah and John M Carroll. 2024. Human–AI Collaboration for Remote Sighted Assistance: Perspectives from the LLM Era. Future Internet 16 7 (2024) 254. · DOI
  63. Omar Zaidan, Jason Eisner, and Christine Piatko. 2007. Using “Annotator Rationales” to Improve Machine Learning for Text Categorization. In Human Language Technologies 2007: The Conference of the North American Chapter of the Association for Computational Linguistics; Proceedings of the Main Conference, Candace Sidner, Tanja Schultz, Matthew Stone, and ChengXiang Zhai (Eds.). Association for Computational Linguistics, Rochester, New York, 260–267. https://aclanthology.org/N07-1033/
  64. 10.18653/v1/2025.acl-long.82 · DOI

Metadata

Authors
Gonzalez Penuela, R. E., Jung, C., Lin, S., Hu, R., & Azenkot, S.
Venue
Proceedings of the 2026 CHI Conference on Human Factors in Computing Systems
Publisher
ACM
Published
2026-04-13
Pages
1-24
Cited by
6
References
10
Funders
NSF (National Science Foundation) (1942693)

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.