<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chung-yu-2023-vlis">
    <titleInfo>
        <title>VLIS: Unimodal Language Models Guide Multimodal Language Generation</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Jiwan</namePart>
        <namePart type="family">Chung</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Youngjae</namePart>
        <namePart type="family">Yu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2023-12</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Houda</namePart>
            <namePart type="family">Bouamor</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Juan</namePart>
            <namePart type="family">Pino</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Kalika</namePart>
            <namePart type="family">Bali</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Singapore</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Multimodal language generation, which leverages the synergy of language and vision, is a rapidly expanding field. However, existing vision-language models face challenges in tasks that require complex linguistic understanding. To address this issue, we introduce Visual-Language models as Importance Sampling weights (VLIS), a novel framework that combines the visual conditioning capability of vision-language models with the language understanding of unimodal text-only language models without further training. It extracts pointwise mutual information of each image and text from a visual-language model and uses the value as an importance sampling weight to adjust the token likelihood from a text-only model. VLIS improves vision-language models on diverse tasks, including commonsense understanding (WHOOPS, OK-VQA, and ScienceQA) and complex text generation (Concadia, Image Paragraph Captioning, and ROCStories). Our results suggest that VLIS represents a promising new direction for multimodal language generation.</abstract>
    <identifier type="citekey">chung-yu-2023-vlis</identifier>
    <identifier type="doi">10.18653/v1/2023.emnlp-main.46</identifier>
    <location>
        <url>https://aclanthology.org/2023.emnlp-main.46</url>
    </location>
    <part>
        <date>2023-12</date>
        <extent unit="page">
            <start>700</start>
            <end>721</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T VLIS: Unimodal Language Models Guide Multimodal Language Generation
%A Chung, Jiwan
%A Yu, Youngjae
%Y Bouamor, Houda
%Y Pino, Juan
%Y Bali, Kalika
%S Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing
%D 2023
%8 December
%I Association for Computational Linguistics
%C Singapore
%F chung-yu-2023-vlis
%X Multimodal language generation, which leverages the synergy of language and vision, is a rapidly expanding field. However, existing vision-language models face challenges in tasks that require complex linguistic understanding. To address this issue, we introduce Visual-Language models as Importance Sampling weights (VLIS), a novel framework that combines the visual conditioning capability of vision-language models with the language understanding of unimodal text-only language models without further training. It extracts pointwise mutual information of each image and text from a visual-language model and uses the value as an importance sampling weight to adjust the token likelihood from a text-only model. VLIS improves vision-language models on diverse tasks, including commonsense understanding (WHOOPS, OK-VQA, and ScienceQA) and complex text generation (Concadia, Image Paragraph Captioning, and ROCStories). Our results suggest that VLIS represents a promising new direction for multimodal language generation.
%R 10.18653/v1/2023.emnlp-main.46
%U https://aclanthology.org/2023.emnlp-main.46
%U https://doi.org/10.18653/v1/2023.emnlp-main.46
%P 700-721

Markdown (Informal)

[VLIS: Unimodal Language Models Guide Multimodal Language Generation](https://aclanthology.org/2023.emnlp-main.46) (Chung & Yu, EMNLP 2023)

• VLIS: Unimodal Language Models Guide Multimodal Language Generation (Chung & Yu, EMNLP 2023)

ACL

• Jiwan Chung and Youngjae Yu. 2023. VLIS: Unimodal Language Models Guide Multimodal Language Generation. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 700–721, Singapore. Association for Computational Linguistics.