Sightation Counts: Leveraging Sighted User Feedback in Building a BLV-aligned Dataset of Diagram Descriptions
Abstract
Often, the needs and visual abilities differ between the annotator group and the end user group. Generating detailed diagram descriptions for blind and low-vision (BLV) users is one such challenging domain. Sighted annotators could describe visuals with ease, but existing studies have shown that direct generations by them are costly, bias-prone, and somewhat lacking by BLV standards. In this study, we ask sighted individuals to assess -- rather than produce -- diagram descriptions generated by vision-language models (VLM) that have been guided with latent supervision via a multi-pass inference. The sighted assessments prove effective and useful to professional educators who are themselves BLV and teach visually impaired learners. We release Sightation, a collection of diagram description datasets spanning 5k diagrams and 137k samples for completion, preference, retrieval, question answering, and reasoning training purposes and demonstrate their fine-tuning potential in various downstream tasks.
Community
We put together a dataset of diagram descriptions for blind and low-vision (BLV) learners. We showed that models trained on our dataset outperform baselines, as verified by BLV professionals at schools for the blind. By releasing the datasets for chat completion, preference learning, retrieval, VQA, and reasoning purposes, we hope to make education more accessible.
This is an automated message from the Librarian Bot. I found the following papers similar to this paper.
The following papers were recommended by the Semantic Scholar API
- Can LVLMs and Automatic Metrics Capture Underlying Preferences of Blind and Low-Vision Individuals for Navigational Aid? (2025)
- VideoA11y: Method and Dataset for Accessible Video Description (2025)
- GuideDog: A Real-World Egocentric Multimodal Dataset for Blind and Low-Vision Accessibility-Aware Guidance (2025)
- Symmetrical Visual Contrastive Optimization: Aligning Vision-Language Models with Minimal Contrastive Images (2025)
- VisCon-100K: Leveraging Contextual Web Data for Fine-tuning Vision Language Models (2025)
- Painting with Words: Elevating Detailed Image Captioning with Benchmark and Alignment Learning (2025)
- Re-Align: Aligning Vision Language Models via Retrieval-Augmented Direct Preference Optimization (2025)
Please give a thumbs up to this comment if you found it helpful!
If you want recommendations for any Paper on Hugging Face checkout this Space
You can directly ask Librarian Bot for paper recommendations by tagging it in a comment:
@librarian-bot
recommend
Models citing this paper 0
No model linking this paper
Datasets citing this paper 5
Browse 5 datasets citing this paperSpaces citing this paper 0
No Space linking this paper