<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhao-etal-2026-towards-automatic">
    <titleInfo>
        <title>Towards Automatic Evolution Tree Generation from Citation Graphs</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Zexing</namePart>
        <namePart type="family">Zhao</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yuntong</namePart>
        <namePart type="family">Hu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Liang</namePart>
        <namePart type="family">Zhao</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>Surveys remain the primary way researchers grasp the lineage of methods within an AI subfield, but they scale poorly against the current rate of publication. Existing taxonomy-induction methods are largely leaf-bound and time-agnostic; they tend to force transitional papers into mature leaves and can create topological inversions between ancestors and descendants. We propose EvoTree, a staged framework that decouples conceptual backbone learning from temporal refinement: a graph-aware encoder with distribution-based hierarchical clustering yields a stable taxonomy backbone; temporal fine-tuning then re-attaches marginal papers to internal nodes under monotonic-path constraints; a final LLM pass labels concepts without altering the topology. We release the first annotated benchmark for this task across 11 AI subfields. EvoTree improves Leaf Purity and Path Monotonicity Rate over the strongest taxonomy-induction baseline, and is the only method with non-trivial marginal-paper detection on the annotated set.</abstract>
    <identifier type="citekey">zhao-etal-2026-towards-automatic</identifier>
    <identifier type="doi">10.18653/2026.findings-emnlp.1351</identifier>
    <location>
        <url>https://aclanthology.org/2026.findings-emnlp.1351/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>28680</start>
            <end>28703</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Towards Automatic Evolution Tree Generation from Citation Graphs
%A Zhao, Zexing
%A Hu, Yuntong
%A Zhao, Liang
%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 zhao-etal-2026-towards-automatic
%X Surveys remain the primary way researchers grasp the lineage of methods within an AI subfield, but they scale poorly against the current rate of publication. Existing taxonomy-induction methods are largely leaf-bound and time-agnostic; they tend to force transitional papers into mature leaves and can create topological inversions between ancestors and descendants. We propose EvoTree, a staged framework that decouples conceptual backbone learning from temporal refinement: a graph-aware encoder with distribution-based hierarchical clustering yields a stable taxonomy backbone; temporal fine-tuning then re-attaches marginal papers to internal nodes under monotonic-path constraints; a final LLM pass labels concepts without altering the topology. We release the first annotated benchmark for this task across 11 AI subfields. EvoTree improves Leaf Purity and Path Monotonicity Rate over the strongest taxonomy-induction baseline, and is the only method with non-trivial marginal-paper detection on the annotated set.
%R 10.18653/2026.findings-emnlp.1351
%U https://aclanthology.org/2026.findings-emnlp.1351/
%U https://doi.org/10.18653/2026.findings-emnlp.1351
%P 28680-28703

Markdown (Informal)

[Towards Automatic Evolution Tree Generation from Citation Graphs](https://aclanthology.org/2026.findings-emnlp.1351/) (Zhao et al., Findings 2026)

• Towards Automatic Evolution Tree Generation from Citation Graphs (Zhao et al., Findings 2026)

ACL

• Zexing Zhao, Yuntong Hu, and Liang Zhao. 2026. Towards Automatic Evolution Tree Generation from Citation Graphs. In Findings of the Association for Computational Linguistics: EMNLP 2026, pages 28680–28703, Budapest, Hungary. Association for Computational Linguistics.