# AD4EDU: Benchmarking University Lecture Audio Description across Accessibility Standards, Metrics, and Learner Preferences

arXiv: https://arxiv.org/abs/2610.17042 · HTML: https://mlsanity.com/paper/2610.17042/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 29 of its 138 references that are in the map.
- First posted on arXiv 12 Oct 2026.

## Builds on (most cited first, 29 of 29)

- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [Robust Speech Recognition via Large-Scale Weak Supervision](https://mlsanity.com/paper/2212.04356/) (2022)
- [CLIPScore: A Reference-free Evaluation Metric for Image Captioning](https://mlsanity.com/paper/2104.08718/) (2021)
- [CIDEr: Consensus-based Image Description Evaluation](https://mlsanity.com/paper/1411.5726/) (2014)
- [A Call for Clarity in Reporting BLEU Scores](https://mlsanity.com/paper/1804.08771/) (2018)
- [A Survey on LLM-as-a-Judge](https://mlsanity.com/paper/2411.15594/) (2024)
- [LLM Evaluators Recognize and Favor Their Own Generations](https://mlsanity.com/paper/2404.13076/) (2024)
- [From Generation to Judgment: Opportunities and Challenges of LLM-as-a-judge](https://mlsanity.com/paper/2411.16594/) (2024)
- [TIFA: Accurate and Interpretable Text-to-Image Faithfulness Evaluation with Question Answering](https://mlsanity.com/paper/2303.11897/) (2023)
- [KTO: Model Alignment as Prospect Theoretic Optimization](https://mlsanity.com/paper/2402.01306/) (2024)
- [SmolVLM: Redefining small and efficient multimodal models](https://mlsanity.com/paper/2504.05299/) (2025)
- [OpenRubrics: Towards Scalable Synthetic Rubric Generation for Reward Modeling and LLM Alignment](https://mlsanity.com/paper/2510.07743/) (2025)
- [AutoAD II: The Sequel -- Who, When, and What in Movie Audio Description](https://mlsanity.com/paper/2310.06838/) (2023)
- [Online DPO: Online Direct Preference Optimization with Fast-Slow Chasing](https://mlsanity.com/paper/2406.05534/) (2024)
- [AutoAD-Zero: A Training-Free Framework for Zero-Shot Audio Description](https://mlsanity.com/paper/2407.15850/) (2024)
- [Rescribe: Authoring and Automatically Editing Audio Descriptions](https://mlsanity.com/paper/2010.03667/) (2020)
- [LLM-AD: Large Language Model based Audio Description System](https://mlsanity.com/paper/2405.00983/) (2024)
- [DistinctAD: Distinctive Audio Description Generation in Contexts](https://mlsanity.com/paper/2411.18180/) (2024)
- ["It's Kind of Context Dependent": Understanding Blind and Low Vision People's Video Accessibility Preferences Across Viewing Scenarios](https://mlsanity.com/paper/2403.10792/) (2024)
- [Multimodal Lecture Presentations Dataset: Understanding Multimodality in Educational Slides](https://mlsanity.com/paper/2208.08080/) (2022)
- [VideoA11y: Method and Dataset for Accessible Video Description](https://mlsanity.com/paper/2502.20480/) (2025)
- [What You See is What You Ask: Evaluating Audio Descriptions](https://mlsanity.com/paper/2510.00808/) (2025)
- [Audio Description Generation in the Era of LLMs and VLMs: A Review of Transferable Generative AI Technologies](https://mlsanity.com/paper/2410.08860/) (2024)
- [Describe Now: User-Driven Audio Description for Blind and Low Vision Individuals](https://mlsanity.com/paper/2411.11835/) (2024)
- [M3AV: A Multimodal, Multigenre, and Multipurpose Audio-Visual Academic Lecture Dataset](https://mlsanity.com/paper/2403.14168/) (2024)
- [ViDscribe: Multimodal AI for Customizing Audio Description and Question Answering in Online Videos](https://mlsanity.com/paper/2603.14662/) (2026)
- [VeasyGuide: Personalized Visual Guidance for Low-vision Learners on Instructor Actions in Presentation Videos](https://mlsanity.com/paper/2507.21837/) (2025)
- [Toward Scalable Audio Description Quality Control: A Workflow for Evaluating Human and VLM Raters](https://mlsanity.com/paper/2602.01390/) (2026)

## Abstract (arXiv)

Audio description (AD) aims to enhance the accessibility of visual media for blind and low-vision (BLV) persons. However, in higher education, where slide-based lectures are a default mode of teaching, lecture AD remains largely underexplored. The main reason is that existing production guidelines, evaluation metrics, and benchmark datasets are oriented toward entertainment content and do not transfer to lectures, where ADs must complement the lecturer's speech, resolve deictic references, and fit within narrow pauses. In this work, we propose AD4Edu, consisting of an AD benchmark, AD4Edu-Bench, and a rule-diagnosable evaluation metric, AD4Edu-Eval, for generating and evaluating ADs in higher education. Specifically, we consolidated established accessibility guidance, including WCAG 2.2, the DCMP Description Key, and NCAM's STEM description practices. We further collected silver reference ADs, judge-ordered preference pairs, and pairwise preferences from four BLV raters, and post-trained models with direct preference optimization (DPO) for detailed analysis. Our findings indicate that while the metric reliably detects violations of the standard, ADs that comply with it do not necessarily fulfill the subjective preferences of BLV persons, most notably on description length, underscoring the necessity of active participation of BLV persons in co-designing inclusive AI solutions.