<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chen-etal-2026-dominance">
    <titleInfo>
        <title>The Dominance of Text Space: Unveiling the Asymmetric Nature of Cross-Modal Alignment in Large Language Models</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Linqing</namePart>
        <namePart type="family">Chen</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Hanmeng</namePart>
        <namePart type="family">Zhong</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Wentao</namePart>
        <namePart type="family">Wu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Peng</namePart>
        <namePart type="family">Zhou</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2026-07</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Maria</namePart>
            <namePart type="family">Liakata</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Viviane</namePart>
            <namePart type="given">P</namePart>
            <namePart type="family">Moreira</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Jiajun</namePart>
            <namePart type="family">Zhang</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">David</namePart>
            <namePart type="family">Jurgens</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">San Diego, California, United States</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-390-6</identifier>
    </relatedItem>
    <abstract>Recent advancements in Multimodal Large Language Models (MLLMs) have largely been driven by aligning visual encoders with pre-trained Large Language Models (LLMs). While effective, the geometric nature of this alignment remains under-explored. Existing methods often assume a symmetric interaction between visual and textual modalities, implying that both spaces adapt to each other. In this paper, we challenge this assumption and propose the “Text Space as Anchor” hypothesis. We argue that the semantic space of LLMs is rigid, anisotropic, and dominant; thus, effective cross-modal alignment may be an asymmetric projection of visual features onto this pre-existing text manifold without distorting it. We identify a potential issue in current parameter-efficient tuning paradigms where task-specific visual adjustments inadvertently disrupt the projector’s geometry, leading to “catastrophic forgetting” of the alignment mechanism itself. To address this, we introduce Anchor-Preserving Projection (APP), a novel method that regularizes the projector to maintain the geometric structure of the text embedding space via spectral filtering. Extensive experiments on 8 diverse cross-modal tasks and 3 pure language benchmarks demonstrate that APP preserves the LLM’s inherent linguistic capabilities (e.g., MMLU, GSM8K) and reduces object hallucination significantly better than standard fine-tuning methods. We release our code.</abstract>
    <identifier type="citekey">chen-etal-2026-dominance</identifier>
    <location>
        <url>https://aclanthology.org/2026.acl-long.1699/</url>
    </location>
    <part>
        <date>2026-07</date>
        <extent unit="page">
            <start>36666</start>
            <end>36678</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T The Dominance of Text Space: Unveiling the Asymmetric Nature of Cross-Modal Alignment in Large Language Models
%A Chen, Linqing
%A Zhong, Hanmeng
%A Wu, Wentao
%A Zhou, Peng
%Y Liakata, Maria
%Y Moreira, Viviane P.
%Y Zhang, Jiajun
%Y Jurgens, David
%S Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, United States
%@ 979-8-89176-390-6
%F chen-etal-2026-dominance
%X Recent advancements in Multimodal Large Language Models (MLLMs) have largely been driven by aligning visual encoders with pre-trained Large Language Models (LLMs). While effective, the geometric nature of this alignment remains under-explored. Existing methods often assume a symmetric interaction between visual and textual modalities, implying that both spaces adapt to each other. In this paper, we challenge this assumption and propose the “Text Space as Anchor” hypothesis. We argue that the semantic space of LLMs is rigid, anisotropic, and dominant; thus, effective cross-modal alignment may be an asymmetric projection of visual features onto this pre-existing text manifold without distorting it. We identify a potential issue in current parameter-efficient tuning paradigms where task-specific visual adjustments inadvertently disrupt the projector’s geometry, leading to “catastrophic forgetting” of the alignment mechanism itself. To address this, we introduce Anchor-Preserving Projection (APP), a novel method that regularizes the projector to maintain the geometric structure of the text embedding space via spectral filtering. Extensive experiments on 8 diverse cross-modal tasks and 3 pure language benchmarks demonstrate that APP preserves the LLM’s inherent linguistic capabilities (e.g., MMLU, GSM8K) and reduces object hallucination significantly better than standard fine-tuning methods. We release our code.
%U https://aclanthology.org/2026.acl-long.1699/
%P 36666-36678

Markdown (Informal)

[The Dominance of Text Space: Unveiling the Asymmetric Nature of Cross-Modal Alignment in Large Language Models](https://aclanthology.org/2026.acl-long.1699/) (Chen et al., ACL 2026)

• The Dominance of Text Space: Unveiling the Asymmetric Nature of Cross-Modal Alignment in Large Language Models (Chen et al., ACL 2026)

ACL

• Linqing Chen, Hanmeng Zhong, Wentao Wu, and Peng Zhou. 2026. The Dominance of Text Space: Unveiling the Asymmetric Nature of Cross-Modal Alignment in Large Language Models. In Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 36666–36678, San Diego, California, United States. Association for Computational Linguistics.