@inproceedings{choi-etal-2026-taxation,
title = "Taxation Perspectives from Large Language Models: A Case Study on Additional Tax Penalties",
author = "Choi, Eunkyung and
Suh, Young Jin and
Lee, Siun and
Oh, Hongseok and
Kang, Juheon and
Hur, Won and
Park, Hun and
Hwang, Wonseok",
editor = "Demberg, Vera and
Inui, Kentaro and
Marquez, Llu{\'i}s",
booktitle = "Proceedings of the 19th Conference of the {E}uropean Chapter of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
month = mar,
year = "2026",
address = "Rabat, Morocco",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.eacl-long.218/",
pages = "4702--4726",
ISBN = "979-8-89176-380-7",
abstract = "How capable are large language models (LLMs) in the domain of taxation? Although numerous studies have explored the legal domain, research dedicated to taxation remains scarce. Moreover, the datasets used in these studies are either simplified, failing to reflect the real-world complexities, or not released as open-source. To address this gap, we introduce PLAT, a new benchmark designed to assess the ability of LLMs to predict the legitimacy of additional tax penalties. PLAT comprises 300 examples: (1) 100 binary-choice questions, (2) 100 multiple-choice questions, and (3) 100 essay-type questions, all derived from 100 Korean court precedents. PLAT is constructed to evaluate not only LLMs' understanding of tax law but also their performance in legal cases that require complex reasoning beyond straight forward application of statutes. Our systematic experiments with multiple LLMs reveal that (1) their baseline capabilities are limited, especially in cases involving conflicting issues that require a comprehensive understanding (not only of the statutes but also of the taxpayer{'}s circumstances), and (2) LLMs struggle particularly with the ``AC'' stages of ``IRAC'' even for advanced reasoning models like o3, which actively employ inference-time scaling."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="choi-etal-2026-taxation">
<titleInfo>
<title>Taxation Perspectives from Large Language Models: A Case Study on Additional Tax Penalties</title>
</titleInfo>
<name type="personal">
<namePart type="given">Eunkyung</namePart>
<namePart type="family">Choi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Young</namePart>
<namePart type="given">Jin</namePart>
<namePart type="family">Suh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Siun</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hongseok</namePart>
<namePart type="family">Oh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Juheon</namePart>
<namePart type="family">Kang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Won</namePart>
<namePart type="family">Hur</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hun</namePart>
<namePart type="family">Park</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wonseok</namePart>
<namePart type="family">Hwang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-03</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Vera</namePart>
<namePart type="family">Demberg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kentaro</namePart>
<namePart type="family">Inui</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lluís</namePart>
<namePart type="family">Marquez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Rabat, Morocco</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-380-7</identifier>
</relatedItem>
<abstract>How capable are large language models (LLMs) in the domain of taxation? Although numerous studies have explored the legal domain, research dedicated to taxation remains scarce. Moreover, the datasets used in these studies are either simplified, failing to reflect the real-world complexities, or not released as open-source. To address this gap, we introduce PLAT, a new benchmark designed to assess the ability of LLMs to predict the legitimacy of additional tax penalties. PLAT comprises 300 examples: (1) 100 binary-choice questions, (2) 100 multiple-choice questions, and (3) 100 essay-type questions, all derived from 100 Korean court precedents. PLAT is constructed to evaluate not only LLMs’ understanding of tax law but also their performance in legal cases that require complex reasoning beyond straight forward application of statutes. Our systematic experiments with multiple LLMs reveal that (1) their baseline capabilities are limited, especially in cases involving conflicting issues that require a comprehensive understanding (not only of the statutes but also of the taxpayer’s circumstances), and (2) LLMs struggle particularly with the “AC” stages of “IRAC” even for advanced reasoning models like o3, which actively employ inference-time scaling.</abstract>
<identifier type="citekey">choi-etal-2026-taxation</identifier>
<location>
<url>https://aclanthology.org/2026.eacl-long.218/</url>
</location>
<part>
<date>2026-03</date>
<extent unit="page">
<start>4702</start>
<end>4726</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Taxation Perspectives from Large Language Models: A Case Study on Additional Tax Penalties
%A Choi, Eunkyung
%A Suh, Young Jin
%A Lee, Siun
%A Oh, Hongseok
%A Kang, Juheon
%A Hur, Won
%A Park, Hun
%A Hwang, Wonseok
%Y Demberg, Vera
%Y Inui, Kentaro
%Y Marquez, Lluís
%S Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2026
%8 March
%I Association for Computational Linguistics
%C Rabat, Morocco
%@ 979-8-89176-380-7
%F choi-etal-2026-taxation
%X How capable are large language models (LLMs) in the domain of taxation? Although numerous studies have explored the legal domain, research dedicated to taxation remains scarce. Moreover, the datasets used in these studies are either simplified, failing to reflect the real-world complexities, or not released as open-source. To address this gap, we introduce PLAT, a new benchmark designed to assess the ability of LLMs to predict the legitimacy of additional tax penalties. PLAT comprises 300 examples: (1) 100 binary-choice questions, (2) 100 multiple-choice questions, and (3) 100 essay-type questions, all derived from 100 Korean court precedents. PLAT is constructed to evaluate not only LLMs’ understanding of tax law but also their performance in legal cases that require complex reasoning beyond straight forward application of statutes. Our systematic experiments with multiple LLMs reveal that (1) their baseline capabilities are limited, especially in cases involving conflicting issues that require a comprehensive understanding (not only of the statutes but also of the taxpayer’s circumstances), and (2) LLMs struggle particularly with the “AC” stages of “IRAC” even for advanced reasoning models like o3, which actively employ inference-time scaling.
%U https://aclanthology.org/2026.eacl-long.218/
%P 4702-4726
Markdown (Informal)
[Taxation Perspectives from Large Language Models: A Case Study on Additional Tax Penalties](https://aclanthology.org/2026.eacl-long.218/) (Choi et al., EACL 2026)
ACL
- Eunkyung Choi, Young Jin Suh, Siun Lee, Hongseok Oh, Juheon Kang, Won Hur, Hun Park, and Wonseok Hwang. 2026. Taxation Perspectives from Large Language Models: A Case Study on Additional Tax Penalties. In Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers), pages 4702–4726, Rabat, Morocco. Association for Computational Linguistics.