<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="xu-ding-2026-scp">
    <titleInfo>
        <title>SCP-ISA: Spatial Cross-attention Projection for Textual Spatial Semantic Anomaly Detection and Attribution</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Bei</namePart>
        <namePart type="family">Xu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Mengqi</namePart>
        <namePart type="family">Ding</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>Findings of the Association for Computational Linguistics: EMNLP 2026</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Hung-Yi</namePart>
            <namePart type="family">Lee</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Sunipa</namePart>
            <namePart type="family">Dev</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Jessy</namePart>
            <namePart type="family">Li</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Desmond</namePart>
            <namePart type="family">Elliott</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">979-8-89176-462-0</identifier>
    </relatedItem>
    <abstract>Textual spatial semantic anomaly detection and attribution requires deciding whether a sentence contains an implausible spatial relation and assigning the corresponding attribution label. Prior prompting and Low-Rank Adaptation (LoRA) fine-tuning methods rely on raw tokenlevel representations, leaving spatial roles and cross-triple conflicts implicit. We propose SCP-ISA, a Spatial Cross-attention Projection (SCP) method with an Inter-Slot Attention (ISA) layer that uses a frozen MacBERT-large encoder to build input-conditioned spatial slots and injects the projected slots into Qwen2.5 as soft prefix embeddings. The ISA layer enables structured cross-slot interaction that collapses co-referring spatial mentions into a shared entity-anchored representation before generation. On the CRSARC benchmark, SCP-ISA improves test cascade attribution F1 (Attr-F1) by 22.7 percentage points (0.509 to 0.736) over Direct LoRA, and detection macro-F1 (Det-F1) from 0.846 to 0.881.</abstract>
    <identifier type="citekey">xu-ding-2026-scp</identifier>
    <identifier type="doi">10.18653/2026.findings-emnlp.1574</identifier>
    <location>
        <url>https://aclanthology.org/2026.findings-emnlp.1574/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>33528</start>
            <end>33534</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T SCP-ISA: Spatial Cross-attention Projection for Textual Spatial Semantic Anomaly Detection and Attribution
%A Xu, Bei
%A Ding, Mengqi
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Findings of the Association for Computational Linguistics: EMNLP 2026
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-462-0
%F xu-ding-2026-scp
%X Textual spatial semantic anomaly detection and attribution requires deciding whether a sentence contains an implausible spatial relation and assigning the corresponding attribution label. Prior prompting and Low-Rank Adaptation (LoRA) fine-tuning methods rely on raw tokenlevel representations, leaving spatial roles and cross-triple conflicts implicit. We propose SCP-ISA, a Spatial Cross-attention Projection (SCP) method with an Inter-Slot Attention (ISA) layer that uses a frozen MacBERT-large encoder to build input-conditioned spatial slots and injects the projected slots into Qwen2.5 as soft prefix embeddings. The ISA layer enables structured cross-slot interaction that collapses co-referring spatial mentions into a shared entity-anchored representation before generation. On the CRSARC benchmark, SCP-ISA improves test cascade attribution F1 (Attr-F1) by 22.7 percentage points (0.509 to 0.736) over Direct LoRA, and detection macro-F1 (Det-F1) from 0.846 to 0.881.
%R 10.18653/2026.findings-emnlp.1574
%U https://aclanthology.org/2026.findings-emnlp.1574/
%U https://doi.org/10.18653/2026.findings-emnlp.1574
%P 33528-33534

Markdown (Informal)

[SCP-ISA: Spatial Cross-attention Projection for Textual Spatial Semantic Anomaly Detection and Attribution](https://aclanthology.org/2026.findings-emnlp.1574/) (Xu & Ding, Findings 2026)

• SCP-ISA: Spatial Cross-attention Projection for Textual Spatial Semantic Anomaly Detection and Attribution (Xu & Ding, Findings 2026)

ACL

• Bei Xu and Mengqi Ding. 2026. SCP-ISA: Spatial Cross-attention Projection for Textual Spatial Semantic Anomaly Detection and Attribution. In Findings of the Association for Computational Linguistics: EMNLP 2026, pages 33528–33534, Budapest, Hungary. Association for Computational Linguistics.