aiqbench analysis
This systematic survey evaluates AI-driven techniques for generating accessible descriptions of STEM visuals, highlighting a critical shift from static alt text to interactive multimodal systems. Despite progress in architectures and interaction modalities, the field still struggles with hallucinations, a lack of co-designed datasets involving visually impaired users, and evaluation metrics that fail to capture real-world trust. The analysis underscores urgent research needs for explainable pipelines and user-controlled verbosity to integrate these tools effectively into STEM education environments.
A Systematic Survey on Image Description Techniques for STEM Domains
arXiv:2607.21611v1 Announce Type: cross Abstract: The proliferation of visual data in Science, Technology, Engineering, and Mathematics (STEM) fields presents accessibility barrier for individuals with blindness or visual impairments. While recent advances in Artificial Intelligence (AI) offer new opportunities to generate textual descriptions of STEM images, the research landscape is fragmented and its impact on real users remains limited. This systematic survey examines 20 peer-reviewed studies on AI-based techniques for describing STEM visuals, with a specific focus on accessibility and human-computer interaction. Following the PRISMA methodology and a ROBIS-based risk-of-bias assessment, the review analyzes (i) the types of STEM visuals targeted, (ii) the AI and machine learning architectures employed, (iii) the datasets and evaluation metrics adopted, and (iv) the interaction modalities through which descriptions are delivered. The analysis reveals a shift from static, one-shot alt text toward interactive and multimodal systems that integrate conversational interfaces, keyboard navigation, and audio or haptic feedback. However, critical challenges persist, including factual inaccuracies and hallucinations, the scarcity of accessibility-first datasets co-designed with blind and low-vision users, and a heavy reliance on automatic text-overlap metrics that poorly capture perceived usefulness and trust. The survey concludes by outlining key research directions for HCI, emphasizing user-controlled verbosity, explainable and verifiable AI pipelines, and the integration of accessible description tools into mainstream STEM authoring and learning environments.
Abstract:The proliferation of visual data in Science, Technology, Engineering, and Mathematics (STEM) fields presents accessibility barrier for individuals with blindness or visual impairments. While recent advances in Artificial Intelligence (AI) offer new opportunities to generate textual descriptions of STEM images, the research landscape is fragmented and its impact on real users remains limited. This systematic survey examines 20 peer-reviewed studies on AI-based techniques for describing STEM visuals, with a specific focus on accessibility and human-computer interaction. Following the PRISMA methodology and a ROBIS-based risk-of-bias assessment, the review analyzes (i) the types of STEM visuals targeted, (ii) the AI and machine learning architectures employed, (iii) the datasets and evaluation metrics adopted, and (iv) the interaction modalities through which descriptions are delivered. The analysis reveals a shift from static, one-shot alt text toward interactive and multimodal systems that integrate conversational interfaces, keyboard navigation, and audio or haptic feedback. However, critical challenges persist, including factual inaccuracies and hallucinations, the scarcity of accessibility-first datasets co-designed with blind and low-vision users, and a heavy reliance on automatic text-overlap metrics that poorly capture perceived usefulness and trust. The survey concludes by outlining key research directions for HCI, emphasizing user-controlled verbosity, explainable and verifiable AI pipelines, and the integration of accessible description tools into mainstream STEM authoring and learning environments.
This is the Author's Original Manuscript of an article accepted for publication in International Journal of Human-Computer Interaction, published by Taylor and Francis. The Version of Record is available at DOI https://doi.org/10.1080/10447318.2026.2668031
Human-Computer Interaction (cs.HC); Artificial Intelligence (cs.AI)
arXiv:2607.21611 [cs.HC]
(or arXiv:2607.21611v1 [cs.HC] for this version)
https://doi.org/10.1080/10447318.2026.2668031 DOI(s) linking to related resources
Full text under the publisher's open licence · 265 words
Related coverage
What's Continual Learning, and Why Might We Expect To See It In Advanced LLM Agents?
LessWrong · Jun 12, 2026
[AINews] not much happened today
Latent Space · Sep 18, 2026
Math Largest Congress Ends Tomorrow : How Logic , Physics , and Geometry Cracked the Oldest Problems
techtimes.com · Jul 29, 2026
Lattice-Based Cryptography Explained
Quantum Zeitgeist · Aug 15, 2026