Cynthia Bennett
Research Areas
Authored Publications
Sort By
Preview abstract
Audio Description ( AD) provides essential access to visual media for blind and low vision ( BLV) audiences. Yet current AD production tools remain largely inaccessible to BLV video creators, who possess valuable expertise but face barriers due to visually- driven interfaces. We present ADCanvas, a multimodal authoring system that supports non- visual control
over audio description ( AD) creation. ADCanvas combines conversational interaction with keyboard- based playback control and a plain- text, screen reader–
accessible editor to support end- to- end AD authoring and visual question answering ( VQA). Combining screen- reader- friendly controls with a multimodal
LLM agent, ADCanvas supports live VQA, script generation, and AD modification. Through a user study with 12 BLV video creators, we find that users adopt
the conversational agent as an informational aide and drafting assistant, while maintaining agency through verification and editing. For example, participants
saw themselves as curators who received information from the model and filtered it down for their audience. Our findings offer design implications for
accessible media tools, including precise editing controls, accessibility support for creative ideation, and configurable rules for human- AI collaboration.
View details
Amplifying Trans and Nonbinary Voices: A Community-Centred Harm Taxonomy for LLMs
Eddie Ungless
Beka Gulotta
Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (2025)
Preview abstract
We explore large language model (LLM) responses that may negatively impact the transgender and nonbinary (TGNB) community and introduce the Transing Transformers Toolkit, T3, which provides resources for identifying such harmful response behaviors. The heart of T3 is a community-centred taxonomy of harms, developed in collaboration with the TGNB community, which we complement with, amongst other guidance, suggested heuristics for evaluation. To develop the taxonomy, we adopted a multi-method approach that included surveys and focus groups with community experts. The contribution highlights the importance of community-centred approaches in mitigating harm, and outlines pathways for LLM developers to improve how their models handle TGNB-related topics.
View details
Toward Community- Led Evaluations of Text-to-Image AI Representations of Disability, Health, and Accessibility
Equity and Access in Algorithms, Mechanisms, and Optimization (EAAMO) (2025)
Preview abstract
Responsible AI advocates for user evaluations, particularly when concerning people with disabilities, health conditions, and accessibility needs ( DHA)–wide- ranging but umbrellaed sociodemograph- ics. However, community- centered text- to- image AI’s ( T2I) evaluations are often researcher- led, situating evaluators as consumers. We instead recruited 21 people with diverse DHA to evaluate T2I by writing and editing their own T2I prompts with their preferred language and topics, in a method mirroring everyday use. We contribute user- generated terminology categories which inform future research and data collections, necessary for developing authentic scaled evaluations. We additionally surface yet- discussed DHA AI harms intersecting race and class, and participants shared harm impacts they experienced as image- creator evaluators. To this end, we demonstrate that prompt engineering– proposed as a misrepresentation mitigation– was largely ineffective at improving DHA representations. We discuss the importance of evaluator agency to increase ecological validity in community- centered evaluations, and opportunities to research iterative prompting as an evaluation technique.
View details
Preview abstract
As public policy advances the rights of people with disabilities, and as corporations begin to recognize disabled people as core market segments, industry practice in accessible technology design and development improves day by day. Yet, as with other research domains there are lags and gaps in the implementation of accessibility between the lab and industry practice. In this panel, we describe multiple barriers to collaboration between academia and industry and how these barriers manifest as issues in implementation of research findings in industry and lack of adoption of best practices in academia, and vice versa. We then discuss how these specific cases complicate the imagined divide between academic and industry approaches to accessibility. How can notions of accessibility be expanded in both contexts to include overlooked dimensions like ethics, dark patterns, and cognition? This discussion moves towards more inclusive, impactful, and actionable accessibility practices across industry, academia, and public policy.
View details
"Accessibility people, you go work on that thing of yours over there": Addressing Disability Inclusion in AI Product Organizations
Sanika Moharana
Erin Buehler
Michael Madaio
Vinita Tibdewal
Proceedings of AIES 2025 (2025) (to appear)
Preview abstract
The rapid emergence of generative AI models and AI powered systems has surfaced a variety of concerns around responsibility, safety, and inclusion. Some of these concerns address specific vulnerable communities, including people with disabilities. At the same time, these systems may introduce harms upon disabled users that do not fit neatly into existing accessibility classifications, and may not be addressed by current accessibility practices. In this paper, we investigate how stakeholders across a variety of job types are encountering and addressing potentially negative impacts of AI on users with disabilities. Through interviews with 25 practitioners, we identify emerging challenges related to AI’s impact on disabled users, systemic obstacles that contribute to problems, and effective strategies for impacting change. Based on these findings, we offer suggestions for improving existing processes for creating AI-powered systems and supporting practitioners in developing skills to address these emerging challenges.
View details
Amplifying Trans and Nonbinary Voices: A Community-Centred Harm Taxonomy for LLMs
Eddie Ungless
Beka Gulotta
Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (2025)
Preview abstract
We explore large language model (LLM) responses that may negatively impact the transgender and nonbinary (TGNB) community and introduce the Transing Transformers Toolkit, T3, which provides resources for identifying such harmful response behaviors. The heart of T3 is a community-centred taxonomy of harms, developed in collaboration with the TGNB community, which we complement with, amongst other guidance, suggested heuristics for evaluation. To develop the taxonomy, we adopted a multi-method approach that included surveys and focus groups with community experts. The contribution highlights the importance of community-centred approaches in mitigating harm, and outlines pathways for LLM developers to improve how their models handle TGNB-related topics.
View details
Preview abstract
Audio description (AD) narrates important visual details which are played during dialogue gaps in video soundtracks, making them accessible to blind and low vision (BLV) audiences. AD professionals (producers, writers, narrators, mixers, and quality control specialists) possess expert knowledge of AD development and the constraints that affect their work. However, their perspectives remain largely absent in AD research. We present interviews with 17 AD professionals (8 BLV), detailing their workflows to produce AD for recorded media and live theater. We additionally explore their perspectives on recent changes impacting their work, revealing tensions between advocacy for culturally competent AD and the rise of automations—some beneficial, others with concerning implications for AD quality. Highlighting these tensions, we offer research directions to support AD professionals, and we pose guiding questions for AD and AI innovators on preserving the high-quality human touch professionals consider fundamental to the accessibility provision.
View details
From Provenance to Aberrations: Image Creator and Screen Reader User Perspectives on Alt Text for AI-Generated Images
Maitraye Das
Alexander J. Fiannaca
CHI Conference on Human Factors in Computing Systems (2024)
Preview abstract
AI-generated images are proliferating as a new visual medium. However, state-of-the-art image generation models do not output alternative (alt) text with
their images, rendering them largely inaccessible to screen reader users (SRUs). Moreover, less is known about what information would be most desirable
to SRUs in this new medium. To address this, we invited AI image creators and SRUs to evaluate alt text prepared from various sources and write their own
alt text for AI images. Our mixed-methods analysis makes three contributions. First, we highlight creators’ perspectives on alt text, as creators are well-positioned
to write descriptions of their images. Second, we illustrate SRUs’ alt text needs particular to the emerging medium of AI images. Finally, we discuss the
promises and pitfalls of utilizing text prompts written as input for AI models in alt text generation, and areas where broader digital accessibility guidelines
could expand to account for AI images.
View details
Understanding Use Cases for AI-Powered Visual Interpretation Services
Ricardo Gonzalez
Jazmin Collins
Shiri Azenkot
CHI Conference on Human-Computer Interaction (2024)
Preview abstract
"Scene description" applications that describe visual content in a photo are useful daily tools for blind and low vision (BLV) people. Researchers have
studied their use, but they have only explored those that leverage remote sighted assistants; little is known about applications that use AI to generate
their descriptions. Thus, to investigate their use cases, we conducted a two-week diary study where 16 BLV participants used an AI-powered scene description
application we designed. Through their diary entries and follow-up interviews, users shared their information goals and assessments of the visual descriptions
they received. We analyzed the entries and found frequent use cases, such as identifying visual features of known objects, and surprising ones, such as avoiding contact with dangerous objects. We also found users scored the descriptions relatively low on average,
2.76 out of 5 (SD=1.49) for satisfaction and 2.43 out of 4 (SD=1.16) for trust, showing that descriptions still need signifcant improvements to deliver
satisfying and trustworthy experiences. We discuss future opportunities for AI as it becomes a more powerful accessibility tool for BLV users.
View details
Preview abstract
Generative AI (GAI) is proliferating, and among its many applications are to support creative work (e.g., generating text, images, music) and to enhance accessibility (e.g., captions of images and audio). As GAI evolves, creatives must consider how (or how not) to incorporate these tools into their practices. In this paper, we present interviews at the intersection of these applications. We learned from 10 creatives with disabilities who intentionally use and do not use GAI in and around their creative work. Their mediums ranged from audio engineering to leatherwork, and they collectively experienced a variety of disabilities, from sensory to motor to invisible disabilities. We share cross-cutting themes of their access hacks, how creative practice and access work become entangled, and their perspectives on how GAI should and should not fit into their workflows. In turn, we offer qualities of accessible creativity with responsible AI that can inform future research.
View details
