@inproceedings{yuan-etal-2026-surveygraph,
title = "{S}urvey{G}raph: Generating Academic Surveys via Methods-Entity Knowledge Graphs",
author = "Yuan, Yifan and
Zhu, Yancheng and
Zhang, Zuoyu and
Peng, Xiaogang",
editor = "Lee, Hung-Yi and
Dev, Sunipa and
Li, Jessy and
Elliott, Desmond",
booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {EMNLP} 2026",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.findings-emnlp.396/",
pages = "8350--8383",
ISBN = "979-8-89176-462-0",
abstract = "Automated survey generation systems increasingly rely on flat retrieval over document collections, limiting their ability to capture the evolutionary structure of research fields. We present SurveyGraph, a framework centered on a Methods-Entity Knowledge Graph (MEKG) that encodes method-level follow-on, competition, and shared-resource relations across papers. The MEKG serves as a unified backbone for core-paper discovery, graph-aware retrieval, hybrid outline generation, and evolutionary narrative synthesis.\par We evaluate SurveyGraph through a multi-level protocol spanning retrieval benchmarks, semantic-edge validation, citation grounding audits, benchmark-facing collection probes, and same-backend generation-stage diagnostics. In a controlled seven-method equal-budget benchmark, MEKG-anchored fusion achieves the best balance of recall and structural density among all tested methods, demonstrating that typed graph structure provides a complementary signal to simpler retrieval approaches. On the archived graph-native core diagnostic, graph-aware retrieval nearly doubles recall over flat lexical baselines across all eight runs (p = 0.004). A semantic evidence gate with AUC = 0.75 filters noisy edges, and citation-grounding audits over 160 generated sentences confirm 80.6{\%} anchored-or-partial support with evidence-level contrasts validating genuine alignment. Human validation over 108 stratified semantic edges (Cohen{'}s {\ensuremath{\kappa}} = 0.64 for the binary support decision) confirms 68.5{\%} supported-or-partial after adjudication, with improves relations strongest at 80.6{\%} and extends weakest at 52.8{\%}. A SurveyBench-facing collection probe reaches 0.521 mean reference coverage on four topics under an eight-paper budget; same-backend Qwen diagnostics over a 30-paper/74-relation MEKG further show that removing hybrid outlining lowers artifact organization signals. We report concurrent-system comparisons only as bounded diagnostics rather than same-backend end-to-end claims. Code and artifacts are available at: https://github.com/xzzvsxd/SurveyGraph."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yuan-etal-2026-surveygraph">
<titleInfo>
<title>SurveyGraph: Generating Academic Surveys via Methods-Entity Knowledge Graphs</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yifan</namePart>
<namePart type="family">Yuan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yancheng</namePart>
<namePart type="family">Zhu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zuoyu</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaogang</namePart>
<namePart type="family">Peng</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>Automated survey generation systems increasingly rely on flat retrieval over document collections, limiting their ability to capture the evolutionary structure of research fields. We present SurveyGraph, a framework centered on a Methods-Entity Knowledge Graph (MEKG) that encodes method-level follow-on, competition, and shared-resource relations across papers. The MEKG serves as a unified backbone for core-paper discovery, graph-aware retrieval, hybrid outline generation, and evolutionary narrative synthesis.\par We evaluate SurveyGraph through a multi-level protocol spanning retrieval benchmarks, semantic-edge validation, citation grounding audits, benchmark-facing collection probes, and same-backend generation-stage diagnostics. In a controlled seven-method equal-budget benchmark, MEKG-anchored fusion achieves the best balance of recall and structural density among all tested methods, demonstrating that typed graph structure provides a complementary signal to simpler retrieval approaches. On the archived graph-native core diagnostic, graph-aware retrieval nearly doubles recall over flat lexical baselines across all eight runs (p = 0.004). A semantic evidence gate with AUC = 0.75 filters noisy edges, and citation-grounding audits over 160 generated sentences confirm 80.6% anchored-or-partial support with evidence-level contrasts validating genuine alignment. Human validation over 108 stratified semantic edges (Cohen’s \ensuremathąppa = 0.64 for the binary support decision) confirms 68.5% supported-or-partial after adjudication, with improves relations strongest at 80.6% and extends weakest at 52.8%. A SurveyBench-facing collection probe reaches 0.521 mean reference coverage on four topics under an eight-paper budget; same-backend Qwen diagnostics over a 30-paper/74-relation MEKG further show that removing hybrid outlining lowers artifact organization signals. We report concurrent-system comparisons only as bounded diagnostics rather than same-backend end-to-end claims. Code and artifacts are available at: https://github.com/xzzvsxd/SurveyGraph.</abstract>
<identifier type="citekey">yuan-etal-2026-surveygraph</identifier>
<location>
<url>https://aclanthology.org/2026.findings-emnlp.396/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>8350</start>
<end>8383</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T SurveyGraph: Generating Academic Surveys via Methods-Entity Knowledge Graphs
%A Yuan, Yifan
%A Zhu, Yancheng
%A Zhang, Zuoyu
%A Peng, Xiaogang
%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 yuan-etal-2026-surveygraph
%X Automated survey generation systems increasingly rely on flat retrieval over document collections, limiting their ability to capture the evolutionary structure of research fields. We present SurveyGraph, a framework centered on a Methods-Entity Knowledge Graph (MEKG) that encodes method-level follow-on, competition, and shared-resource relations across papers. The MEKG serves as a unified backbone for core-paper discovery, graph-aware retrieval, hybrid outline generation, and evolutionary narrative synthesis.\par We evaluate SurveyGraph through a multi-level protocol spanning retrieval benchmarks, semantic-edge validation, citation grounding audits, benchmark-facing collection probes, and same-backend generation-stage diagnostics. In a controlled seven-method equal-budget benchmark, MEKG-anchored fusion achieves the best balance of recall and structural density among all tested methods, demonstrating that typed graph structure provides a complementary signal to simpler retrieval approaches. On the archived graph-native core diagnostic, graph-aware retrieval nearly doubles recall over flat lexical baselines across all eight runs (p = 0.004). A semantic evidence gate with AUC = 0.75 filters noisy edges, and citation-grounding audits over 160 generated sentences confirm 80.6% anchored-or-partial support with evidence-level contrasts validating genuine alignment. Human validation over 108 stratified semantic edges (Cohen’s \ensuremathąppa = 0.64 for the binary support decision) confirms 68.5% supported-or-partial after adjudication, with improves relations strongest at 80.6% and extends weakest at 52.8%. A SurveyBench-facing collection probe reaches 0.521 mean reference coverage on four topics under an eight-paper budget; same-backend Qwen diagnostics over a 30-paper/74-relation MEKG further show that removing hybrid outlining lowers artifact organization signals. We report concurrent-system comparisons only as bounded diagnostics rather than same-backend end-to-end claims. Code and artifacts are available at: https://github.com/xzzvsxd/SurveyGraph.
%U https://aclanthology.org/2026.findings-emnlp.396/
%P 8350-8383
Markdown (Informal)
[SurveyGraph: Generating Academic Surveys via Methods-Entity Knowledge Graphs](https://aclanthology.org/2026.findings-emnlp.396/) (Yuan et al., Findings 2026)
ACL