@inproceedings{mandiga-2026-non,
title = "A Non-Visual Baseline for Multi-View Visual Question Answering on {G}olden{V}iew{VQA}",
author = "Mandiga, Aravind",
editor = "Wang, Yimu and
Choi, Yee Man and
Wu, Di and
Ouyang, Siqi and
Azadani, Mozhgan Nasr and
Fung, Yi R. (May)",
booktitle = "Proceedings of the 1st Workshop on Grounding Language Models: Learning Faithfully and Efficiently ({G}round{LM} 2026)",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.groundlm-1.83/",
pages = "1162--1167",
ISBN = "979-8-89176-478-1",
abstract = "We present a non-visual baseline for GoldenViewVQA, a benchmark for multi-view visual question answering with evidence-source identification. The baseline reaches a joint accuracy of 0.7119 on the hidden test split and uses no visual input. Its view prediction is the fixed label CAM{\_}FRONT, which reaches 0.7797 view accuracy on the test split, while Qwen3-4B predicts the answer from the question, answer options, and non-visual metadata with 0.8475 answer accuracy. These results show that the current benchmark permits substantial performance without image access. We analyze the supporting-view prior and performance across question groups, and discuss benchmark changes that could reduce reliance on non-visual shortcuts. We present this run as a strong non-visual baseline, not as evidence that vision is unnecessary for driving question answering. Code: https://github.com/aravind-mandiga/groundlm-goldenviewvqa."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="mandiga-2026-non">
<titleInfo>
<title>A Non-Visual Baseline for Multi-View Visual Question Answering on GoldenViewVQA</title>
</titleInfo>
<name type="personal">
<namePart type="given">Aravind</namePart>
<namePart type="family">Mandiga</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 1st Workshop on Grounding Language Models: Learning Faithfully and Efficiently (GroundLM 2026)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yimu</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yee</namePart>
<namePart type="given">Man</namePart>
<namePart type="family">Choi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Di</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Siqi</namePart>
<namePart type="family">Ouyang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mozhgan</namePart>
<namePart type="given">Nasr</namePart>
<namePart type="family">Azadani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yi</namePart>
<namePart type="given">R</namePart>
<namePart type="given">(May)</namePart>
<namePart type="family">Fung</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Budapest, Hungary</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-478-1</identifier>
</relatedItem>
<abstract>We present a non-visual baseline for GoldenViewVQA, a benchmark for multi-view visual question answering with evidence-source identification. The baseline reaches a joint accuracy of 0.7119 on the hidden test split and uses no visual input. Its view prediction is the fixed label CAM_FRONT, which reaches 0.7797 view accuracy on the test split, while Qwen3-4B predicts the answer from the question, answer options, and non-visual metadata with 0.8475 answer accuracy. These results show that the current benchmark permits substantial performance without image access. We analyze the supporting-view prior and performance across question groups, and discuss benchmark changes that could reduce reliance on non-visual shortcuts. We present this run as a strong non-visual baseline, not as evidence that vision is unnecessary for driving question answering. Code: https://github.com/aravind-mandiga/groundlm-goldenviewvqa.</abstract>
<identifier type="citekey">mandiga-2026-non</identifier>
<location>
<url>https://aclanthology.org/2026.groundlm-1.83/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>1162</start>
<end>1167</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Non-Visual Baseline for Multi-View Visual Question Answering on GoldenViewVQA
%A Mandiga, Aravind
%Y Wang, Yimu
%Y Choi, Yee Man
%Y Wu, Di
%Y Ouyang, Siqi
%Y Azadani, Mozhgan Nasr
%Y Fung, Yi R. (May)
%S Proceedings of the 1st Workshop on Grounding Language Models: Learning Faithfully and Efficiently (GroundLM 2026)
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-478-1
%F mandiga-2026-non
%X We present a non-visual baseline for GoldenViewVQA, a benchmark for multi-view visual question answering with evidence-source identification. The baseline reaches a joint accuracy of 0.7119 on the hidden test split and uses no visual input. Its view prediction is the fixed label CAM_FRONT, which reaches 0.7797 view accuracy on the test split, while Qwen3-4B predicts the answer from the question, answer options, and non-visual metadata with 0.8475 answer accuracy. These results show that the current benchmark permits substantial performance without image access. We analyze the supporting-view prior and performance across question groups, and discuss benchmark changes that could reduce reliance on non-visual shortcuts. We present this run as a strong non-visual baseline, not as evidence that vision is unnecessary for driving question answering. Code: https://github.com/aravind-mandiga/groundlm-goldenviewvqa.
%U https://aclanthology.org/2026.groundlm-1.83/
%P 1162-1167
Markdown (Informal)
[A Non-Visual Baseline for Multi-View Visual Question Answering on GoldenViewVQA](https://aclanthology.org/2026.groundlm-1.83/) (Mandiga, GroundLM 2026)
ACL