<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="baghel-etal-2025-towards">
    <titleInfo>
        <title>Towards Blind and Low-Vision Accessibility of Lightweight VLMs and Custom LLM-Evals</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Shruti</namePart>
        <namePart type="given">Singh</namePart>
        <namePart type="family">Baghel</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yash</namePart>
        <namePart type="given">Pratap</namePart>
        <namePart type="given">Singh</namePart>
        <namePart type="family">Rathore</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Anurag</namePart>
        <namePart type="family">Pradhan</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Sushovan</namePart>
        <namePart type="family">Jena</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Arnav</namePart>
        <namePart type="family">Bhavsar</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Amit</namePart>
        <namePart type="family">Shukla</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Pawan</namePart>
        <namePart type="family">Goyal</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2025-12</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 1st Workshop on Multimodal Models for Low-Resource Contexts and Social Impact (MMLoSo 2025)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Ankita</namePart>
            <namePart type="family">Shukla</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Sandeep</namePart>
            <namePart type="family">Kumar</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Amrit</namePart>
            <namePart type="given">Singh</namePart>
            <namePart type="family">Bedi</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Tanmoy</namePart>
            <namePart type="family">Chakraborty</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Mumbai, India</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-311-1</identifier>
    </relatedItem>
    <abstract>Large Vision-Language Models (VLMs) excel at understanding and generating video descriptions but their high memory, computation, and deployment demands hinder practical use particularly for blind and low-vision (BLV) users who depend on detailed, context-aware descriptions. To study the effect of model size on accessibility-focused description quality, we evaluate SmolVLM2 variants with 500M and 2.2B parameters across two diverse datasets: AVCaps (outdoor), and Charades (indoor). In this work, we introduce two novel evaluation frameworks specifically designed for BLV accessibility assessment: the Multi-Context BLV Framework evaluating spatial orientation, social interaction, action events, and ambience contexts; and the Navigational Assistance Framework focusing on mobility-critical information. Additionally, we conduct a systematic evaluation of four different prompt design strategies and deploy both models on a smartphone, evaluating FP32 and INT8 precision variants to assess real-world performance constraints on resource-limited mobile devices.</abstract>
    <identifier type="citekey">baghel-etal-2025-towards</identifier>
    <location>
        <url>https://aclanthology.org/2025.mmloso-1.8/</url>
    </location>
    <part>
        <date>2025-12</date>
        <extent unit="page">
            <start>86</start>
            <end>94</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Towards Blind and Low-Vision Accessibility of Lightweight VLMs and Custom LLM-Evals
%A Baghel, Shruti Singh
%A Rathore, Yash Pratap Singh
%A Pradhan, Anurag
%A Jena, Sushovan
%A Bhavsar, Arnav
%A Shukla, Amit
%A Goyal, Pawan
%Y Shukla, Ankita
%Y Kumar, Sandeep
%Y Bedi, Amrit Singh
%Y Chakraborty, Tanmoy
%S Proceedings of the 1st Workshop on Multimodal Models for Low-Resource Contexts and Social Impact (MMLoSo 2025)
%D 2025
%8 December
%I Association for Computational Linguistics
%C Mumbai, India
%@ 979-8-89176-311-1
%F baghel-etal-2025-towards
%X Large Vision-Language Models (VLMs) excel at understanding and generating video descriptions but their high memory, computation, and deployment demands hinder practical use particularly for blind and low-vision (BLV) users who depend on detailed, context-aware descriptions. To study the effect of model size on accessibility-focused description quality, we evaluate SmolVLM2 variants with 500M and 2.2B parameters across two diverse datasets: AVCaps (outdoor), and Charades (indoor). In this work, we introduce two novel evaluation frameworks specifically designed for BLV accessibility assessment: the Multi-Context BLV Framework evaluating spatial orientation, social interaction, action events, and ambience contexts; and the Navigational Assistance Framework focusing on mobility-critical information. Additionally, we conduct a systematic evaluation of four different prompt design strategies and deploy both models on a smartphone, evaluating FP32 and INT8 precision variants to assess real-world performance constraints on resource-limited mobile devices.
%U https://aclanthology.org/2025.mmloso-1.8/
%P 86-94

Markdown (Informal)

[Towards Blind and Low-Vision Accessibility of Lightweight VLMs and Custom LLM-Evals](https://aclanthology.org/2025.mmloso-1.8/) (Baghel et al., MMLoSo 2025)

• Towards Blind and Low-Vision Accessibility of Lightweight VLMs and Custom LLM-Evals (Baghel et al., MMLoSo 2025)

ACL

• Shruti Singh Baghel, Yash Pratap Singh Rathore, Anurag Pradhan, Sushovan Jena, Arnav Bhavsar, Amit Shukla, and Pawan Goyal. 2025. Towards Blind and Low-Vision Accessibility of Lightweight VLMs and Custom LLM-Evals. In Proceedings of the 1st Workshop on Multimodal Models for Low-Resource Contexts and Social Impact (MMLoSo 2025), pages 86–94, Mumbai, India. Association for Computational Linguistics.