@inproceedings{iwamoto-etal-2026-empirical,
title = "An Empirical Analysis of Factual Errors in Human-Written Text and Its Application to Factual Error Detection",
author = "Iwamoto, Kazuma and
Omura, Kazumasa and
Ishihara, Shotaro",
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.2337/",
pages = "50250--50264",
ISBN = "979-8-89176-462-0",
abstract = "Factual Error Detection (FED), which is the task of identifying factually incorrect spans in a given text, has long been recognized as an important research problem. However, with the rapid rise of large language models (LLMs), research attention has shifted toward factual errors specific to LLM-generated text (hallucinations) and their detection. As a result, the detection of factual errors in human-written text has been relatively neglected. To address this gap, we first distill a taxonomy of human-induced factual errors by analyzing corrections of newspaper articles, a representative source of text that is guaranteed to be human-written and contains few grammatical errors. Our analysis revealed that there are characteristic categories such as kanji misconversions and numeral classifier errors, which are not focused in existing hallucination benchmarks. Based on the taxonomy, we then evaluate the FED capability of vanilla LLMs on synthesized realistic test cases and real corrections. Experimental results demonstrated that even high-performance LLMs such as GPT-5.4 achieved only a word-level F1 score of 52{\%} on the synthetic evaluation data, highlighting the task difficulty. Furthermore, a detailed analysis by detection difficulty revealed the current state of FED."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="iwamoto-etal-2026-empirical">
<titleInfo>
<title>An Empirical Analysis of Factual Errors in Human-Written Text and Its Application to Factual Error Detection</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kazuma</namePart>
<namePart type="family">Iwamoto</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kazumasa</namePart>
<namePart type="family">Omura</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shotaro</namePart>
<namePart type="family">Ishihara</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>Factual Error Detection (FED), which is the task of identifying factually incorrect spans in a given text, has long been recognized as an important research problem. However, with the rapid rise of large language models (LLMs), research attention has shifted toward factual errors specific to LLM-generated text (hallucinations) and their detection. As a result, the detection of factual errors in human-written text has been relatively neglected. To address this gap, we first distill a taxonomy of human-induced factual errors by analyzing corrections of newspaper articles, a representative source of text that is guaranteed to be human-written and contains few grammatical errors. Our analysis revealed that there are characteristic categories such as kanji misconversions and numeral classifier errors, which are not focused in existing hallucination benchmarks. Based on the taxonomy, we then evaluate the FED capability of vanilla LLMs on synthesized realistic test cases and real corrections. Experimental results demonstrated that even high-performance LLMs such as GPT-5.4 achieved only a word-level F1 score of 52% on the synthetic evaluation data, highlighting the task difficulty. Furthermore, a detailed analysis by detection difficulty revealed the current state of FED.</abstract>
<identifier type="citekey">iwamoto-etal-2026-empirical</identifier>
<location>
<url>https://aclanthology.org/2026.findings-emnlp.2337/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>50250</start>
<end>50264</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T An Empirical Analysis of Factual Errors in Human-Written Text and Its Application to Factual Error Detection
%A Iwamoto, Kazuma
%A Omura, Kazumasa
%A Ishihara, Shotaro
%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 iwamoto-etal-2026-empirical
%X Factual Error Detection (FED), which is the task of identifying factually incorrect spans in a given text, has long been recognized as an important research problem. However, with the rapid rise of large language models (LLMs), research attention has shifted toward factual errors specific to LLM-generated text (hallucinations) and their detection. As a result, the detection of factual errors in human-written text has been relatively neglected. To address this gap, we first distill a taxonomy of human-induced factual errors by analyzing corrections of newspaper articles, a representative source of text that is guaranteed to be human-written and contains few grammatical errors. Our analysis revealed that there are characteristic categories such as kanji misconversions and numeral classifier errors, which are not focused in existing hallucination benchmarks. Based on the taxonomy, we then evaluate the FED capability of vanilla LLMs on synthesized realistic test cases and real corrections. Experimental results demonstrated that even high-performance LLMs such as GPT-5.4 achieved only a word-level F1 score of 52% on the synthetic evaluation data, highlighting the task difficulty. Furthermore, a detailed analysis by detection difficulty revealed the current state of FED.
%U https://aclanthology.org/2026.findings-emnlp.2337/
%P 50250-50264
Markdown (Informal)
[An Empirical Analysis of Factual Errors in Human-Written Text and Its Application to Factual Error Detection](https://aclanthology.org/2026.findings-emnlp.2337/) (Iwamoto et al., Findings 2026)
ACL