Modeling Triplet Interactions Beyond Pairwise Attention

Mafizur Rahman; Lijun Qian

Modeling Triplet Interactions Beyond Pairwise Attention

Correct Metadata for

Use this form to create a GitHub issue with structured data describing the correction. You will need a GitHub account. Once you create that issue, the correction will be reviewed by a staff member.

⚠️ Mobile Users: Submitting this form to create a new issue will only work with github.com, not the GitHub Mobile app.

Important: The Anthology treat PDFs as authoritative. Please use this form only to correct data that is out of line with the PDF. See our corrections guidelines if you need to change the PDF.

Title Adjust the title. Retain tags such as <fixed-case>.

Authors Adjust author names and order to match the PDF.

Abstract Correct abstract if needed. Retain XML formatting tags such as <tex-math>. You may use ... for bold, ... for italic, ... for underline, <sc>...</sc> for small-caps, <tt>...<tt> for typewriter text, <url>...</url> for URLs, <a href=...> for hyperlinks, and <par/> for paragraph breaks.

Verification against PDF Ensure that the new title/authors match the snapshot below. (If there is no snapshot or it is too small, consult the PDF.)

Authors concatenated from the text boxes above:

ALL author names match the snapshot above—including middle initials, hyphens, and accents.

Abstract

Standard transformers use pairwise (2D) self-attention, which models only token-to-token interactions. Sparse attention reduces computational cost while keeping the same pairwise structure and cannot capture richer multi-token interactions. Therefore, we propose Higher-Order Block Attention (HOBA), which models explicit triplet interactions using structured 3D attention with block-diagonal unrolling. This design remains computationally efficient while extending attention beyond pairwise relations. Additionally, we demonstrate that cross-block interaction improves HOBA performance by supporting long-range token dependencies beyond triplet modeling. Experiments on ten NLP benchmarks across five tasks show that HOBA consistently outperforms dense and sparse 2D baselines.

Anthology ID:: 2026.findings-aacl.101
Volume:: Findings of the Association for Computational Linguistics: IJCNLP-AACL 2026
Month:: November
Year:: 2026
Address:: Hengqin, China
Editors:: Yue Zhang, Ruifeng Xu, Ayu Purwarianti, Tong Rong, Jun Suzuki
Venue:: Findings
SIG:
Publisher:: Association for Computational Linguistics
Note:
Pages:: 2010–2026
Language:
URL:: https://aclanthology.org/2026.findings-aacl.101/
DOI:
Bibkey:
Cite (ACL):: Mafizur Rahman and Lijun Qian. 2026. Modeling Triplet Interactions Beyond Pairwise Attention. In Findings of the Association for Computational Linguistics: IJCNLP-AACL 2026, pages 2010–2026, Hengqin, China. Association for Computational Linguistics.
Cite (Informal):: Modeling Triplet Interactions Beyond Pairwise Attention (Rahman & Qian, Findings 2026)
Copy Citation:
PDF:: https://aclanthology.org/2026.findings-aacl.101.pdf

PDF Cite Search Fix data

Export citation

BibTeX
MODS XML
Endnote
Preformatted

@inproceedings{rahman-qian-2026-modeling,
    title = "Modeling Triplet Interactions Beyond Pairwise Attention",
    author = "Rahman, Mafizur  and
      Qian, Lijun",
    editor = "Zhang, Yue  and
      Xu, Ruifeng  and
      Purwarianti, Ayu  and
      Rong, Tong  and
      Suzuki, Jun",
    booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {IJCNLP}-{AACL} 2026",
    month = nov,
    year = "2026",
    address = "Hengqin, China",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2026.findings-aacl.101/",
    pages = "2010--2026",
    ISBN = "979-8-89176-444-6",
    abstract = "Standard transformers use pairwise (2D) self-attention, which models only token-to-token interactions. Sparse attention reduces computational cost while keeping the same pairwise structure and cannot capture richer multi-token interactions. Therefore, we propose Higher-Order Block Attention (HOBA), which models explicit triplet interactions using structured 3D attention with block-diagonal unrolling. This design remains computationally efficient while extending attention beyond pairwise relations. Additionally, we demonstrate that cross-block interaction improves HOBA performance by supporting long-range token dependencies beyond triplet modeling. Experiments on ten NLP benchmarks across five tasks show that HOBA consistently outperforms dense and sparse 2D baselines."
}

Download as File

<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="rahman-qian-2026-modeling">
    <titleInfo>
        <title>Modeling Triplet Interactions Beyond Pairwise Attention</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Mafizur</namePart>
        <namePart type="family">Rahman</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Lijun</namePart>
        <namePart type="family">Qian</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2026-11</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Findings of the Association for Computational Linguistics: IJCNLP-AACL 2026</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Yue</namePart>
            <namePart type="family">Zhang</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Ruifeng</namePart>
            <namePart type="family">Xu</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Ayu</namePart>
            <namePart type="family">Purwarianti</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Tong</namePart>
            <namePart type="family">Rong</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Jun</namePart>
            <namePart type="family">Suzuki</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Hengqin, China</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-444-6</identifier>
    </relatedItem>
    <abstract>Standard transformers use pairwise (2D) self-attention, which models only token-to-token interactions. Sparse attention reduces computational cost while keeping the same pairwise structure and cannot capture richer multi-token interactions. Therefore, we propose Higher-Order Block Attention (HOBA), which models explicit triplet interactions using structured 3D attention with block-diagonal unrolling. This design remains computationally efficient while extending attention beyond pairwise relations. Additionally, we demonstrate that cross-block interaction improves HOBA performance by supporting long-range token dependencies beyond triplet modeling. Experiments on ten NLP benchmarks across five tasks show that HOBA consistently outperforms dense and sparse 2D baselines.</abstract>
    <identifier type="citekey">rahman-qian-2026-modeling</identifier>
    <location>
        <url>https://aclanthology.org/2026.findings-aacl.101/</url>
    </location>
    <part>
        <date>2026-11</date>
        <extent unit="page">
            <start>2010</start>
            <end>2026</end>
        </extent>
    </part>
</mods>
</modsCollection>

Download as File

%0 Conference Proceedings
%T Modeling Triplet Interactions Beyond Pairwise Attention
%A Rahman, Mafizur
%A Qian, Lijun
%Y Zhang, Yue
%Y Xu, Ruifeng
%Y Purwarianti, Ayu
%Y Rong, Tong
%Y Suzuki, Jun
%S Findings of the Association for Computational Linguistics: IJCNLP-AACL 2026
%D 2026
%8 November
%I Association for Computational Linguistics
%C Hengqin, China
%@ 979-8-89176-444-6
%F rahman-qian-2026-modeling
%X Standard transformers use pairwise (2D) self-attention, which models only token-to-token interactions. Sparse attention reduces computational cost while keeping the same pairwise structure and cannot capture richer multi-token interactions. Therefore, we propose Higher-Order Block Attention (HOBA), which models explicit triplet interactions using structured 3D attention with block-diagonal unrolling. This design remains computationally efficient while extending attention beyond pairwise relations. Additionally, we demonstrate that cross-block interaction improves HOBA performance by supporting long-range token dependencies beyond triplet modeling. Experiments on ten NLP benchmarks across five tasks show that HOBA consistently outperforms dense and sparse 2D baselines.
%U https://aclanthology.org/2026.findings-aacl.101/
%P 2010-2026

Download as File

Markdown (Informal)

[Modeling Triplet Interactions Beyond Pairwise Attention](https://aclanthology.org/2026.findings-aacl.101/) (Rahman & Qian, Findings 2026)

Modeling Triplet Interactions Beyond Pairwise Attention (Rahman & Qian, Findings 2026)

ACL

Mafizur Rahman and Lijun Qian. 2026. Modeling Triplet Interactions Beyond Pairwise Attention. In Findings of the Association for Computational Linguistics: IJCNLP-AACL 2026, pages 2010–2026, Hengqin, China. Association for Computational Linguistics.