Literature Reviews
Reviewed research papers, articles, and publications relevant to digital accessibility.
61 results found tagged large language models.
-
CARTGPT: Real-Time Correction of CART Captions Using Large Language Models
This paper introduces CARTGPT, a real-time system that enhances Communication Access Realtime Translation (CART) captions by combining human-generated CART transcripts with automatic speech recognition (ASR) output and using GPT-4 to detect and corre…
-
DescribePro: Collaborative Audio Description with Human-AI Interaction
This paper presents DescribePro, a web-based platform that combines human expertise with AI capabilities to create and refine audio descriptions (AD) for video content. The system addresses the fundamental tension in AD production: human-crafted desc…
-
Surfacing Variations to Calibrate Perceived Reliability of MLLM-generated Image Descriptions
This paper addresses a critical safety problem in AI-powered visual access technology: multimodal large language models (MLLMs) like GPT-4o, Gemini, and Claude produce fluent, confident image descriptions that can contain fabricated content, misinter…
-
CapTune: Adapting Non-Speech Captions With Anchored Generative Models
CapTune is a system that enables customization of non-speech captions—descriptions of environmental sounds, music, and other audio cues—for Deaf and Hard of Hearing (DHH) viewers. Current captioning practices follow a one-size-fits-all model based on…
-
Check Now, Can You See It?: Exploring Voice and Video-Capable Language Models for Identifying and Spatially Locating Items of Interest for Blind and Low-Vision Travelers
This experience report documents the lived experiences of two blind travelers — Aziz (28, blind in left eye, 20/2200 in right) and JooYoung (35, blind in right eye, limited vision in left) — as they adapted commercially available voice and video-capa…
-
AccessGuru: Leveraging LLMs to Detect and Correct Web Accessibility Violations in HTML Code
This paper introduces AccessGuru, a novel method that combines traditional automated accessibility testing tools with large language models (LLMs) to both detect and correct web accessibility violations in HTML code. The work addresses a persistent g…
-
Benchmarking PDF Accessibility Evaluation: A Dataset and Framework for Assessing Automated and LLM-Based Approaches for Accessibility Testing
This paper addresses a critical gap in PDF accessibility evaluation by introducing the first expert-validated benchmark dataset and standardized evaluation framework for assessing how well different tools and approaches can evaluate PDF accessibility…
-
NeuroBridge: Using Generative AI to Bridge Cross-neurotype Communication Differences through Neurotypical Perspective-taking
This paper presents NeuroBridge, an LLM-powered interactive platform designed to help neurotypical individuals better understand autistic communication styles and reflect on their own role in cross-neurotype communication breakdowns. The system is gr…
-
TwIPS: A Large Language Model Powered Texting Application to Simplify Conversational Nuances for Autistic Users
This paper presents TwIPS, a prototype texting application powered by a large language model that assists autistic users with the pragmatic and tonal aspects of text-based communication. Many autistic individuals experience difficulties interpreting …
-
MAIDR Meets AI: Exploring Multimodal LLM-Based Data Visualization Interpretation by and with Blind and Low-Vision Users
This paper investigates how blind and low-vision (BLV) users interact with large language models to interpret data visualizations, building on the authors' previously developed MAIDR (Multimodal Access and Interactive Data Representation) framework. …