mlsanityData to 7 Oct 2026

How Blind and Low-Vision Individuals Prefer Large Vision-Language Model-Generated Scene Descriptions

arXiv 2502.14883 ↗First posted 15 Feb 2025cs.CV cs.AIcited by 0

On the map: Multimodal LLMs / vision-language models → VLM benchmarks and visual reasoning

Abstract (arXiv)

For individuals with blindness or low vision (BLV), navigating complex environments can pose serious risks. Large Vision-Language Models (LVLMs) show promise for generating scene descriptions, but their effectiveness for BLV users remains underexplored. To address this gap, we conducted a user study with eight BLV participants to systematically evaluate preferences for six types of LVLM descriptions. While they helped to reduce fear and improve actionability, user ratings showed wide variation in sufficiency and conciseness. Furthermore, GPT-4o--despite its strong potential to refine descriptions--was not consistently preferred by participants. We use the insights obtained from the user study to build training data for building our new automatic evaluation metric that can capture BLV preferences effectively. Our findings underscore the urgent need for BLV-centered evaluation metrics and human-in-the-loop feedback to advance LVLM description quality for accessibility.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in VLM benchmarks and visual reasoning, one of 16 directions in Multimodal LLMs / vision-language models. Builds on 21 of its 75 references that are in the map. First posted on arXiv 15 Feb 2025.

Builds on

21 of 75 references.

Closest ancestors · 2

Same direction, newest first

  1. 2024WalkVLM:Aid Visually Impaired People Walking by Vision Language Model30 Dec
  2. 2023OpenFlamingo: An Open-Source Framework for Training Large Autoregressive Vision-Language Models2 Aug

Other references · 19

  1. 2023GPT-4 Technical Reportcited by 18,132
  2. 2023Visual Instruction Tuningcited by 7,792
  3. 2024Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolutioncited by 4,151
  4. 2023Evaluating Object Hallucination in Large Vision-Language Modelscited by 1,696
  5. 2024InternLM-XComposer2: Mastering Free-form Text-Image Composition and Comprehension in Vision-Language Large Modelcited by 326
  6. 2018Touchdown: Natural Language Navigation and Spatial Reasoning in Visual Street Environmentscited by 238
  7. 2021A Good Prompt Is Worth Millions of Parameters: Low-resource Prompt-based Learning for Vision-Language Modelscited by 101
  8. 2021The Factual Inconsistency Problem in Abstractive Text Summarization: A Surveycited by 79
  9. 2022Generative Visual Prompt: Unifying Distributional Control of Pre-Trained Generative Modelscited by 27
  10. 2024VIAssist: Adapting Multi-modal Large Language Models for Users with Visual Impairmentscited by 24
  11. 2024VIALM: A Survey and Benchmark of Visually Impaired Assistance with Large Modelscited by 23
  12. 2024Positive-Augmented Contrastive Learning for Vision-and-Language Evaluation and Trainingcited by 16
7 more
  1. 2024VisionGPT: LLM-Assisted Real-Time Anomaly Detection for Safe Visual Navigationcited by 13
  2. 2019Structured Modeling of Joint Deep Feature and Prediction Refinement for Salient Object Detectioncited by 11
  3. 2024Generating Contextually-Relevant Navigation Instructions for Blind and Low Vision Peoplecited by 7
  4. 2024I0T: Embedding Standardization Method Towards Zero Modality Gapcited by 7
  5. 2024BIV-Priv-Seg: Locating Private Content in Images Taken by People With Visual Impairmentscited by 5
  6. 2024ObjectFinder: An Open-Vocabulary Assistive System for Interactive Object Search by Blind Peoplecited by 5
  7. 2024Updating CLIP to Prefer Descriptions Over Captionscited by 3

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Are Large Vision-Language Models Ready to Guide Blind and Low-Vision Individuals?
  2. 2026How Multimodal Large Language Models Support Access to Visual Information: A Diary Study With Blind and Low Vision People
  3. 2025VideoA11y: Method and Dataset for Accessible Video Description
  4. 2025Surfacing Variations to Calibrate Perceived Reliability of MLLM-generated Image Descriptions
  5. 2025Towards Blind and Low-Vision Accessibility of Lightweight VLMs and Custom LLM-Evals
  6. 2025Guiding Multimodal Large Language Models with Blind and Low Vision People Visual Questions for Proactive Visual Interpretations
  7. 2024Vision-Language Models under Cultural and Inclusive Considerations
  8. 2025Sightation Counts: Leveraging Sighted User Feedback in Building a BLV-aligned Dataset of Diagram Descriptions