<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="niu-etal-2026-chartreg">
    <titleInfo>
        <title>ChartREG++: Benchmarking and Improving Chart Referring Expression Grounding under Diverse referring clues and Multi-Target Referring</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Tianhao</namePart>
        <namePart type="family">Niu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Ziyu</namePart>
        <namePart type="family">Han</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Xuan</namePart>
        <namePart type="family">Dong</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Qingfu</namePart>
        <namePart type="family">Zhu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Wanxiang</namePart>
        <namePart type="family">Che</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>Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing</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">979-8-89176-459-0</identifier>
    </relatedItem>
    <abstract>Referring expression grounding is a core problem in visual grounding and is widely used as a diagnostic of spatial grounding and reasoning in vision–language models, yet most prior work focuses on natural images. In contrast, existing chart referring expression grounding-related benchmarks remain limited: (1) they largely adopt bounding boxes, constraining localization precision for fine chart elements; (2) they mostly assume one and two referred target instances, failing to handle multi-instance target references; (3) the language expressions over-rely on textual cues or data-ranking clues in the chart; (4) they cover only a narrow range of chart types. To address these issues, we introduce a chart referring expression grounding benchmark that first systematically supports multiple localization formats, multiple referred targets, diverse grounding cues and diverse chart types. Results across representative multi-modal large models reveal a significant performance gap. We further introduce an LLM-free synthesis pipeline that exploits the inherent alignment between matplotlib internal artist hierarchy and rendered chart primitives to derive pixel-accurate, multi-granularity instance segmentation masks. We train an instance segmentation model with the synthesized masks and integrate it into a general-purpose multi-modal grounding framework. The resulting system consistently outperforms baselines on our benchmark and generalizes well to a ChartQA-derived real-chart grounding benchmark.</abstract>
    <identifier type="citekey">niu-etal-2026-chartreg</identifier>
    <location>
        <url>https://aclanthology.org/2026.emnlp-main.1485/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>33945</start>
            <end>33969</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T ChartREG++: Benchmarking and Improving Chart Referring Expression Grounding under Diverse referring clues and Multi-Target Referring
%A Niu, Tianhao
%A Han, Ziyu
%A Dong, Xuan
%A Zhu, Qingfu
%A Che, Wanxiang
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-459-0
%F niu-etal-2026-chartreg
%X Referring expression grounding is a core problem in visual grounding and is widely used as a diagnostic of spatial grounding and reasoning in vision–language models, yet most prior work focuses on natural images. In contrast, existing chart referring expression grounding-related benchmarks remain limited: (1) they largely adopt bounding boxes, constraining localization precision for fine chart elements; (2) they mostly assume one and two referred target instances, failing to handle multi-instance target references; (3) the language expressions over-rely on textual cues or data-ranking clues in the chart; (4) they cover only a narrow range of chart types. To address these issues, we introduce a chart referring expression grounding benchmark that first systematically supports multiple localization formats, multiple referred targets, diverse grounding cues and diverse chart types. Results across representative multi-modal large models reveal a significant performance gap. We further introduce an LLM-free synthesis pipeline that exploits the inherent alignment between matplotlib internal artist hierarchy and rendered chart primitives to derive pixel-accurate, multi-granularity instance segmentation masks. We train an instance segmentation model with the synthesized masks and integrate it into a general-purpose multi-modal grounding framework. The resulting system consistently outperforms baselines on our benchmark and generalizes well to a ChartQA-derived real-chart grounding benchmark.
%U https://aclanthology.org/2026.emnlp-main.1485/
%P 33945-33969

Markdown (Informal)

[ChartREG++: Benchmarking and Improving Chart Referring Expression Grounding under Diverse referring clues and Multi-Target Referring](https://aclanthology.org/2026.emnlp-main.1485/) (Niu et al., EMNLP 2026)

• ChartREG++: Benchmarking and Improving Chart Referring Expression Grounding under Diverse referring clues and Multi-Target Referring (Niu et al., EMNLP 2026)

ACL

• Tianhao Niu, Ziyu Han, Xuan Dong, Qingfu Zhu, and Wanxiang Che. 2026. ChartREG++: Benchmarking and Improving Chart Referring Expression Grounding under Diverse referring clues and Multi-Target Referring. In Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing, pages 33945–33969, Budapest, Hungary. Association for Computational Linguistics.