@inproceedings{zhong-etal-2026-dreaming,
title = "Dreaming Up Authors: Factual Prevalence and {LLM} Hallucinations in Academic Authorship Attribution",
author = "Zhong, Sijia and
Yirga, Tamir and
Ma, Yijia and
Le, Thai and
Hu, Yifan",
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.2372/",
pages = "53827--53863",
ISBN = "979-8-89176-459-0",
abstract = "Large Language Models (LLMs) are widely used for question answering but are prone to hallucinations, yet the underlying causes, particularly the role of factual prevalence in training data, remain underexplored. In this work, we study this through academic authorship attribution, hypothesizing that hallucinations are more likely for less prevalent papers. Using citation count as a proxy for factual prevalence, we curate a dataset of 1.92 million papers across eight scientific disciplines with stratified samples by citation level. Experiments on three state-of-the-art LLMs confirm our hypothesis, revealing a robust inverse relationship between hallucination rate and citation count across all models and disciplines, with hallucination rates exceeding 98{\%} for rarely cited papers and falling below 37{\%} for highly cited ones. Our in-depth analysis further shows that these failures primarily reflect retrieval limitations rather than knowledge absence, and hidden-state probing of open-source models shows that factual prevalence is encoded in pre-generation representations, providing convergent mechanistic evidence for the prevalence-hallucination relationship."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhong-etal-2026-dreaming">
<titleInfo>
<title>Dreaming Up Authors: Factual Prevalence and LLM Hallucinations in Academic Authorship Attribution</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sijia</namePart>
<namePart type="family">Zhong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tamir</namePart>
<namePart type="family">Yirga</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yijia</namePart>
<namePart type="family">Ma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thai</namePart>
<namePart type="family">Le</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yifan</namePart>
<namePart type="family">Hu</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 widely used for question answering but are prone to hallucinations, yet the underlying causes, particularly the role of factual prevalence in training data, remain underexplored. In this work, we study this through academic authorship attribution, hypothesizing that hallucinations are more likely for less prevalent papers. Using citation count as a proxy for factual prevalence, we curate a dataset of 1.92 million papers across eight scientific disciplines with stratified samples by citation level. Experiments on three state-of-the-art LLMs confirm our hypothesis, revealing a robust inverse relationship between hallucination rate and citation count across all models and disciplines, with hallucination rates exceeding 98% for rarely cited papers and falling below 37% for highly cited ones. Our in-depth analysis further shows that these failures primarily reflect retrieval limitations rather than knowledge absence, and hidden-state probing of open-source models shows that factual prevalence is encoded in pre-generation representations, providing convergent mechanistic evidence for the prevalence-hallucination relationship.</abstract>
<identifier type="citekey">zhong-etal-2026-dreaming</identifier>
<location>
<url>https://aclanthology.org/2026.emnlp-main.2372/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>53827</start>
<end>53863</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Dreaming Up Authors: Factual Prevalence and LLM Hallucinations in Academic Authorship Attribution
%A Zhong, Sijia
%A Yirga, Tamir
%A Ma, Yijia
%A Le, Thai
%A Hu, Yifan
%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 zhong-etal-2026-dreaming
%X Large Language Models (LLMs) are widely used for question answering but are prone to hallucinations, yet the underlying causes, particularly the role of factual prevalence in training data, remain underexplored. In this work, we study this through academic authorship attribution, hypothesizing that hallucinations are more likely for less prevalent papers. Using citation count as a proxy for factual prevalence, we curate a dataset of 1.92 million papers across eight scientific disciplines with stratified samples by citation level. Experiments on three state-of-the-art LLMs confirm our hypothesis, revealing a robust inverse relationship between hallucination rate and citation count across all models and disciplines, with hallucination rates exceeding 98% for rarely cited papers and falling below 37% for highly cited ones. Our in-depth analysis further shows that these failures primarily reflect retrieval limitations rather than knowledge absence, and hidden-state probing of open-source models shows that factual prevalence is encoded in pre-generation representations, providing convergent mechanistic evidence for the prevalence-hallucination relationship.
%U https://aclanthology.org/2026.emnlp-main.2372/
%P 53827-53863
Markdown (Informal)
[Dreaming Up Authors: Factual Prevalence and LLM Hallucinations in Academic Authorship Attribution](https://aclanthology.org/2026.emnlp-main.2372/) (Zhong et al., EMNLP 2026)
ACL