@inproceedings{oh-etal-2026-show,
title = "Show Me How You Cite: Citation Fidelity, Usage, and Topology in the Evidence Behavior of {AI} Scientific Writing",
author = "Oh, Jihwan and
Sun, Gyeonghun and
Kim, Jisoo and
Lee, Yuho and
Yun, Taewon and
Shin, Jisu and
Song, Hwanjun",
editor = "Lee, Hung-Yi and
Dev, Sunipa and
Li, Jessy and
Elliott, Desmond",
booktitle = "Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.emnlp-main.2063/",
pages = "46978--47004",
ISBN = "979-8-89176-459-0",
abstract = "Large language models (LLMs) are increasingly used in scientific writing, yet their citation behavior remains poorly understood. We introduce CiteSpectrum, a controlled dataset for analyzing citations across five levels of AI involvement, from LLM-Only generation to Human-Authored papers. Using citation-behavior features across fidelity, usage, and topology, we show that AI-generated papers differ from human-written papers in how citations are validated, grounded, used, and structurally organized. Even when retrieval and human guidance reduce ghost citations, AI-generated papers contain more unsupported claims, rely on front-section evidence, use citations more affirmatively, and form broader but less interconnected reference networks. Moreover, citation behavior alone enables a lightweight classifier to outperform strong text-based detectors, achieving 0.880 balanced accuracy and 0.944 AUROC. These results suggest that citation behavior provides a strong, interpretable signal of AI involvement beyond conventional textual patterns. The dataset is available at: https://github.com/DISL-Lab/CiteSpectrum-EMNLP26."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="oh-etal-2026-show">
<titleInfo>
<title>Show Me How You Cite: Citation Fidelity, Usage, and Topology in the Evidence Behavior of AI Scientific Writing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jihwan</namePart>
<namePart type="family">Oh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gyeonghun</namePart>
<namePart type="family">Sun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jisoo</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuho</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Taewon</namePart>
<namePart type="family">Yun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jisu</namePart>
<namePart type="family">Shin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hwanjun</namePart>
<namePart type="family">Song</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>Large language models (LLMs) are increasingly used in scientific writing, yet their citation behavior remains poorly understood. We introduce CiteSpectrum, a controlled dataset for analyzing citations across five levels of AI involvement, from LLM-Only generation to Human-Authored papers. Using citation-behavior features across fidelity, usage, and topology, we show that AI-generated papers differ from human-written papers in how citations are validated, grounded, used, and structurally organized. Even when retrieval and human guidance reduce ghost citations, AI-generated papers contain more unsupported claims, rely on front-section evidence, use citations more affirmatively, and form broader but less interconnected reference networks. Moreover, citation behavior alone enables a lightweight classifier to outperform strong text-based detectors, achieving 0.880 balanced accuracy and 0.944 AUROC. These results suggest that citation behavior provides a strong, interpretable signal of AI involvement beyond conventional textual patterns. The dataset is available at: https://github.com/DISL-Lab/CiteSpectrum-EMNLP26.</abstract>
<identifier type="citekey">oh-etal-2026-show</identifier>
<location>
<url>https://aclanthology.org/2026.emnlp-main.2063/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>46978</start>
<end>47004</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Show Me How You Cite: Citation Fidelity, Usage, and Topology in the Evidence Behavior of AI Scientific Writing
%A Oh, Jihwan
%A Sun, Gyeonghun
%A Kim, Jisoo
%A Lee, Yuho
%A Yun, Taewon
%A Shin, Jisu
%A Song, Hwanjun
%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 oh-etal-2026-show
%X Large language models (LLMs) are increasingly used in scientific writing, yet their citation behavior remains poorly understood. We introduce CiteSpectrum, a controlled dataset for analyzing citations across five levels of AI involvement, from LLM-Only generation to Human-Authored papers. Using citation-behavior features across fidelity, usage, and topology, we show that AI-generated papers differ from human-written papers in how citations are validated, grounded, used, and structurally organized. Even when retrieval and human guidance reduce ghost citations, AI-generated papers contain more unsupported claims, rely on front-section evidence, use citations more affirmatively, and form broader but less interconnected reference networks. Moreover, citation behavior alone enables a lightweight classifier to outperform strong text-based detectors, achieving 0.880 balanced accuracy and 0.944 AUROC. These results suggest that citation behavior provides a strong, interpretable signal of AI involvement beyond conventional textual patterns. The dataset is available at: https://github.com/DISL-Lab/CiteSpectrum-EMNLP26.
%U https://aclanthology.org/2026.emnlp-main.2063/
%P 46978-47004
Markdown (Informal)
[Show Me How You Cite: Citation Fidelity, Usage, and Topology in the Evidence Behavior of AI Scientific Writing](https://aclanthology.org/2026.emnlp-main.2063/) (Oh et al., EMNLP 2026)
ACL
- Jihwan Oh, Gyeonghun Sun, Jisoo Kim, Yuho Lee, Taewon Yun, Jisu Shin, and Hwanjun Song. 2026. Show Me How You Cite: Citation Fidelity, Usage, and Topology in the Evidence Behavior of AI Scientific Writing. In Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing, pages 46978–47004, Budapest, Hungary. Association for Computational Linguistics.