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

arXiv: https://arxiv.org/abs/2502.14883 · HTML: https://mlsanity.com/paper/2502.14883/

## Key facts

- No citing papers in the map yet (data through 14 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.

## Placed in

- Multimodal LLMs / vision-language models / [VLM benchmarks and visual reasoning](https://mlsanity.com/mllm/vlm-benchmarks-and-visual-reasoning/)

## Builds on (most cited first, 21 of 21)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution](https://mlsanity.com/paper/2409.12191/) (2024)
- [Evaluating Object Hallucination in Large Vision-Language Models](https://mlsanity.com/paper/2305.10355/) (2023)
- [OpenFlamingo: An Open-Source Framework for Training Large Autoregressive Vision-Language Models](https://mlsanity.com/paper/2308.01390/) (2023)
- [InternLM-XComposer2: Mastering Free-form Text-Image Composition and Comprehension in Vision-Language Large Model](https://mlsanity.com/paper/2401.16420/) (2024)
- [Touchdown: Natural Language Navigation and Spatial Reasoning in Visual Street Environments](https://mlsanity.com/paper/1811.12354/) (2018)
- [A Good Prompt Is Worth Millions of Parameters: Low-resource Prompt-based Learning for Vision-Language Models](https://mlsanity.com/paper/2110.08484/) (2021)
- [The Factual Inconsistency Problem in Abstractive Text Summarization: A Survey](https://mlsanity.com/paper/2104.14839/) (2021)
- [Generative Visual Prompt: Unifying Distributional Control of Pre-Trained Generative Models](https://mlsanity.com/paper/2209.06970/) (2022)
- [VIAssist: Adapting Multi-modal Large Language Models for Users with Visual Impairments](https://mlsanity.com/paper/2404.02508/) (2024)
- [VIALM: A Survey and Benchmark of Visually Impaired Assistance with Large Models](https://mlsanity.com/paper/2402.01735/) (2024)
- [Positive-Augmented Contrastive Learning for Vision-and-Language Evaluation and Training](https://mlsanity.com/paper/2410.07336/) (2024)
- [VisionGPT: LLM-Assisted Real-Time Anomaly Detection for Safe Visual Navigation](https://mlsanity.com/paper/2403.12415/) (2024)
- [WalkVLM:Aid Visually Impaired People Walking by Vision Language Model](https://mlsanity.com/paper/2412.20903/) (2024)
- [Structured Modeling of Joint Deep Feature and Prediction Refinement for Salient Object Detection](https://mlsanity.com/paper/1909.04366/) (2019)
- [I0T: Embedding Standardization Method Towards Zero Modality Gap](https://mlsanity.com/paper/2412.14384/) (2024)
- [Generating Contextually-Relevant Navigation Instructions for Blind and Low Vision People](https://mlsanity.com/paper/2407.08219/) (2024)
- [BIV-Priv-Seg: Locating Private Content in Images Taken by People With Visual Impairments](https://mlsanity.com/paper/2407.18243/) (2024)
- [ObjectFinder: An Open-Vocabulary Assistive System for Interactive Object Search by Blind People](https://mlsanity.com/paper/2412.03118/) (2024)
- [Updating CLIP to Prefer Descriptions Over Captions](https://mlsanity.com/paper/2406.09458/) (2024)

## 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.