@inproceedings{sakamoto-etal-2025-development,
title = "Development of Numerical Error Detection Tasks to Analyze the Numerical Capabilities of Language Models",
author = "Sakamoto, Taku and
Sugawara, Saku and
Aizawa, Akiko",
editor = "Rambow, Owen and
Wanner, Leo and
Apidianaki, Marianna and
Al-Khalifa, Hend and
Eugenio, Barbara Di and
Schockaert, Steven",
booktitle = "Proceedings of the 31st International Conference on Computational Linguistics",
month = jan,
year = "2025",
address = "Abu Dhabi, UAE",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.coling-main.666/",
pages = "9957--9976",
abstract = "Numbers are used to describe quantities in various scenarios in daily life; therefore, numerical errors can significantly affect the meaning of the entire sentence, and even a single-letter error can be fatal. Detecting numerical errors often requires a high level of commonsense and is difficult even with the recent large language models (LLMs). In this study, we create a benchmark dataset of numerical error detection that uses automatically generated numerical errors. In our analysis, we classify the numerical errors based on the properties of the errors and investigate the ability of the model from several perspectives, including the error class, error size, and passage domain. The experimental results indicate that GPT-3.5, GPT-4, and Llama-3-Instruct (8B) perform well in the numerical error detection task; however, they are not as accurate as humans. We find that the LLMs misidentified correct numbers as errors more frequently than the humans did. In particular, the analysis demonstrates that the current LLMs still need improvement for detecting numerical errors requiring calculations or extensive prior knowledge."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sakamoto-etal-2025-development">
<titleInfo>
<title>Development of Numerical Error Detection Tasks to Analyze the Numerical Capabilities of Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Taku</namePart>
<namePart type="family">Sakamoto</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Saku</namePart>
<namePart type="family">Sugawara</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Akiko</namePart>
<namePart type="family">Aizawa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-01</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 31st International Conference on Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Owen</namePart>
<namePart type="family">Rambow</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Leo</namePart>
<namePart type="family">Wanner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marianna</namePart>
<namePart type="family">Apidianaki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hend</namePart>
<namePart type="family">Al-Khalifa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Barbara</namePart>
<namePart type="given">Di</namePart>
<namePart type="family">Eugenio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Steven</namePart>
<namePart type="family">Schockaert</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Abu Dhabi, UAE</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Numbers are used to describe quantities in various scenarios in daily life; therefore, numerical errors can significantly affect the meaning of the entire sentence, and even a single-letter error can be fatal. Detecting numerical errors often requires a high level of commonsense and is difficult even with the recent large language models (LLMs). In this study, we create a benchmark dataset of numerical error detection that uses automatically generated numerical errors. In our analysis, we classify the numerical errors based on the properties of the errors and investigate the ability of the model from several perspectives, including the error class, error size, and passage domain. The experimental results indicate that GPT-3.5, GPT-4, and Llama-3-Instruct (8B) perform well in the numerical error detection task; however, they are not as accurate as humans. We find that the LLMs misidentified correct numbers as errors more frequently than the humans did. In particular, the analysis demonstrates that the current LLMs still need improvement for detecting numerical errors requiring calculations or extensive prior knowledge.</abstract>
<identifier type="citekey">sakamoto-etal-2025-development</identifier>
<location>
<url>https://aclanthology.org/2025.coling-main.666/</url>
</location>
<part>
<date>2025-01</date>
<extent unit="page">
<start>9957</start>
<end>9976</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Development of Numerical Error Detection Tasks to Analyze the Numerical Capabilities of Language Models
%A Sakamoto, Taku
%A Sugawara, Saku
%A Aizawa, Akiko
%Y Rambow, Owen
%Y Wanner, Leo
%Y Apidianaki, Marianna
%Y Al-Khalifa, Hend
%Y Eugenio, Barbara Di
%Y Schockaert, Steven
%S Proceedings of the 31st International Conference on Computational Linguistics
%D 2025
%8 January
%I Association for Computational Linguistics
%C Abu Dhabi, UAE
%F sakamoto-etal-2025-development
%X Numbers are used to describe quantities in various scenarios in daily life; therefore, numerical errors can significantly affect the meaning of the entire sentence, and even a single-letter error can be fatal. Detecting numerical errors often requires a high level of commonsense and is difficult even with the recent large language models (LLMs). In this study, we create a benchmark dataset of numerical error detection that uses automatically generated numerical errors. In our analysis, we classify the numerical errors based on the properties of the errors and investigate the ability of the model from several perspectives, including the error class, error size, and passage domain. The experimental results indicate that GPT-3.5, GPT-4, and Llama-3-Instruct (8B) perform well in the numerical error detection task; however, they are not as accurate as humans. We find that the LLMs misidentified correct numbers as errors more frequently than the humans did. In particular, the analysis demonstrates that the current LLMs still need improvement for detecting numerical errors requiring calculations or extensive prior knowledge.
%U https://aclanthology.org/2025.coling-main.666/
%P 9957-9976
Markdown (Informal)
[Development of Numerical Error Detection Tasks to Analyze the Numerical Capabilities of Language Models](https://aclanthology.org/2025.coling-main.666/) (Sakamoto et al., COLING 2025)
ACL