# BLaVe-CoT: Consistency-Aware Visual Question Answering for Blind and Low Vision Users

arXiv: https://arxiv.org/abs/2509.06010 · HTML: https://mlsanity.com/paper/2509.06010/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 21 references that are in the map.
- First posted on arXiv 7 Sep 2025.

## Builds on (most cited first, 12 of 12)

- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models](https://mlsanity.com/paper/2301.12597/) (2023)
- [MiniLM: Deep Self-Attention Distillation for Task-Agnostic Compression of Pre-Trained Transformers](https://mlsanity.com/paper/2002.10957/) (2020)
- [VizWiz Grand Challenge: Answering Visual Questions from Blind People](https://mlsanity.com/paper/1802.08218/) (2018)
- [PolyFormer: Referring Image Segmentation as Sequential Polygon Generation](https://mlsanity.com/paper/2302.07387/) (2023)
- [Dynamic Conceptional Contrastive Learning for Generalized Category Discovery](https://mlsanity.com/paper/2303.17393/) (2023)
- [Natural Language Understanding and Inference with MLLM in Visual Question Answering: A Survey](https://mlsanity.com/paper/2411.17558/) (2024)
- [Consistency and Uncertainty: Identifying Unreliable Responses From Black-Box Vision-Language Models for Selective Visual Question Answering](https://mlsanity.com/paper/2404.10193/) (2024)
- [VQA Therapy: Exploring Answer Differences by Visually Grounding Answers](https://mlsanity.com/paper/2308.11662/) (2023)
- [A survey on VQA_Datasets and Approaches](https://mlsanity.com/paper/2105.00421/) (2021)
- [Towards Understanding the Use of MLLM-Enabled Applications for Visual Interpretation by Blind and Low Vision People](https://mlsanity.com/paper/2503.05899/) (2025)
- [DARE: Diverse Visual Question Answering with Robustness Evaluation](https://mlsanity.com/paper/2409.18023/) (2024)

## Built on by (most cited first, 1 of 1)

- [How Much Does It Cost to Answer My Question? Benchmarking Cloud VLM-based VQA Systems](https://mlsanity.com/paper/2608.07861/) (2026)

## Abstract (arXiv)

Visual Question Answering (VQA) holds great potential for assisting Blind and Low Vision (BLV) users, yet real-world usage remains challenging. Due to visual impairments, BLV users often take blurry or poorly framed photos and face difficulty in articulating specific questions about what they cannot fully see. As a result, their visual questions are frequently ambiguous, and different users may interpret them in diverse ways. This leads to multiple valid answers, each grounded in different image regions-posing a mismatch with conventional VQA systems that assume a single answer and region. To bridge this gap, we present BLaVe-CoT, a VQA framework designed to reason about answer consistency in the face of ambiguity. Our method proposes diverse candidate answers using a LoRA-tuned BLIP-2 model, then grounds each answer spatially using PolyFormer, and finally applies a chain-of-thought reasoning module to assess whether the answers refer to the same or different regions. Evaluated on the VQA-AnswerTherapy benchmark, BLaVe-CoT outperforms previous methods and proves more robust to the ambiguity and visual noise common in assistive settings. This work highlights the need for VQA systems that can adapt to real human uncertainty and provide inclusive support for BLV users. To foster further research and accessibility applications, we have made the code publicly available at https://github.com/Accecwan/BLaVe-CoT.