@inproceedings{ziyang-etal-2024-vga,
title = "{VGA}: Vision {GUI} Assistant - Minimizing Hallucinations through Image-Centric Fine-Tuning",
author = "Ziyang, Meng and
Dai, Yu and
Gong, Zezheng and
Guo, Shaoxiong and
Tang, Minglong and
Wei, Tongquan",
editor = "Al-Onaizan, Yaser and
Bansal, Mohit and
Chen, Yun-Nung",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2024",
month = nov,
year = "2024",
address = "Miami, Florida, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.findings-emnlp.68",
pages = "1261--1279",
abstract = "Large Vision-Language Models (VLMs) have already been applied to the understanding of Graphical User Interfaces (GUIs) and have achieved notable results. However, existing VLMs often overly rely on internal text-based knowledge while neglecting visual inputs. This imbalance may lead models to produce answers that do not align with the visual content in GUI comprehension tasks. Such inaccuracies are termed as {`}hallucinations{'} where models generate incorrect or illogical responses upon visual verification against GUI elements. These errors result in misinterpretations and diminish the model{'}s practical utility in applied settings. To address these issues, we introduce VGA, a fine-tuned model designed for comprehensive GUI understanding. Our model aims to balance attention image and text to enhance interpretation and reduce hallucinations. We construct a Vision Question Answering (VQA) dataset of 63.8k high-quality examples with our propose *Referent Method*, focusing on response with visual content of images. We then design a two-stage fine-tuning method to enhance both the model{'}s accuracy to extract information from image content and alignment with human intent. Experiments show that our approach enhances the model{'}s ability to extract information from images and achieves state-of-the-art results in GUI understanding tasks. https://github.com/Linziyang1999/VGA-visual-GUI-assistant",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ziyang-etal-2024-vga">
<titleInfo>
<title>VGA: Vision GUI Assistant - Minimizing Hallucinations through Image-Centric Fine-Tuning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Meng</namePart>
<namePart type="family">Ziyang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yu</namePart>
<namePart type="family">Dai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zezheng</namePart>
<namePart type="family">Gong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shaoxiong</namePart>
<namePart type="family">Guo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Minglong</namePart>
<namePart type="family">Tang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tongquan</namePart>
<namePart type="family">Wei</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2024</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yaser</namePart>
<namePart type="family">Al-Onaizan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohit</namePart>
<namePart type="family">Bansal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yun-Nung</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Miami, Florida, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Large Vision-Language Models (VLMs) have already been applied to the understanding of Graphical User Interfaces (GUIs) and have achieved notable results. However, existing VLMs often overly rely on internal text-based knowledge while neglecting visual inputs. This imbalance may lead models to produce answers that do not align with the visual content in GUI comprehension tasks. Such inaccuracies are termed as ‘hallucinations’ where models generate incorrect or illogical responses upon visual verification against GUI elements. These errors result in misinterpretations and diminish the model’s practical utility in applied settings. To address these issues, we introduce VGA, a fine-tuned model designed for comprehensive GUI understanding. Our model aims to balance attention image and text to enhance interpretation and reduce hallucinations. We construct a Vision Question Answering (VQA) dataset of 63.8k high-quality examples with our propose *Referent Method*, focusing on response with visual content of images. We then design a two-stage fine-tuning method to enhance both the model’s accuracy to extract information from image content and alignment with human intent. Experiments show that our approach enhances the model’s ability to extract information from images and achieves state-of-the-art results in GUI understanding tasks. https://github.com/Linziyang1999/VGA-visual-GUI-assistant</abstract>
<identifier type="citekey">ziyang-etal-2024-vga</identifier>
<location>
<url>https://aclanthology.org/2024.findings-emnlp.68</url>
</location>
<part>
<date>2024-11</date>
<extent unit="page">
<start>1261</start>
<end>1279</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T VGA: Vision GUI Assistant - Minimizing Hallucinations through Image-Centric Fine-Tuning
%A Ziyang, Meng
%A Dai, Yu
%A Gong, Zezheng
%A Guo, Shaoxiong
%A Tang, Minglong
%A Wei, Tongquan
%Y Al-Onaizan, Yaser
%Y Bansal, Mohit
%Y Chen, Yun-Nung
%S Findings of the Association for Computational Linguistics: EMNLP 2024
%D 2024
%8 November
%I Association for Computational Linguistics
%C Miami, Florida, USA
%F ziyang-etal-2024-vga
%X Large Vision-Language Models (VLMs) have already been applied to the understanding of Graphical User Interfaces (GUIs) and have achieved notable results. However, existing VLMs often overly rely on internal text-based knowledge while neglecting visual inputs. This imbalance may lead models to produce answers that do not align with the visual content in GUI comprehension tasks. Such inaccuracies are termed as ‘hallucinations’ where models generate incorrect or illogical responses upon visual verification against GUI elements. These errors result in misinterpretations and diminish the model’s practical utility in applied settings. To address these issues, we introduce VGA, a fine-tuned model designed for comprehensive GUI understanding. Our model aims to balance attention image and text to enhance interpretation and reduce hallucinations. We construct a Vision Question Answering (VQA) dataset of 63.8k high-quality examples with our propose *Referent Method*, focusing on response with visual content of images. We then design a two-stage fine-tuning method to enhance both the model’s accuracy to extract information from image content and alignment with human intent. Experiments show that our approach enhances the model’s ability to extract information from images and achieves state-of-the-art results in GUI understanding tasks. https://github.com/Linziyang1999/VGA-visual-GUI-assistant
%U https://aclanthology.org/2024.findings-emnlp.68
%P 1261-1279
Markdown (Informal)
[VGA: Vision GUI Assistant - Minimizing Hallucinations through Image-Centric Fine-Tuning](https://aclanthology.org/2024.findings-emnlp.68) (Ziyang et al., Findings 2024)
ACL