@inproceedings{lim-etal-2026-kfineval,
title = "{KF}in{E}val: A Curated Benchmark Suite for Real-World {K}orean Financial Language Understanding",
author = "Lim, Seonkyu and
Hwang, Bokwang and
Baek, Jonghyuk and
Kim, Jingu and
Yoo, Hangyeol and
Lim, KyungTae",
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.286/",
pages = "6049--6081",
ISBN = "979-8-89176-462-0",
abstract = "We introduce KFinEval, a benchmark for evaluating large language models (LLMs) in the Korean financial domain, with about 1K expert-curated instances across foundational financial knowledge, regulation-grounded procedural reasoning under noisy contexts, and financial toxicity under adversarial prompts. Existing financial benchmarks are largely English-centric and emphasize numerical or surface reasoning, providing limited coverage of regulation-grounded decision-making and domain-specific safety. Evaluating proprietary and open-weight LLMs, we observe substantial disparities and trade-offs among knowledge accuracy, procedural reasoning, and safety-aligned behavior; notably, strong capability does not consistently translate into safer responses under adversarial financial scenarios. KFinEval provides a practical Korean-regulation-grounded benchmark for diagnosing and improving financial LLM reliability and safety. Code and resources: https://github.com/sklim84/KFinEval."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lim-etal-2026-kfineval">
<titleInfo>
<title>KFinEval: A Curated Benchmark Suite for Real-World Korean Financial Language Understanding</title>
</titleInfo>
<name type="personal">
<namePart type="given">Seonkyu</namePart>
<namePart type="family">Lim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bokwang</namePart>
<namePart type="family">Hwang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jonghyuk</namePart>
<namePart type="family">Baek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jingu</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hangyeol</namePart>
<namePart type="family">Yoo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">KyungTae</namePart>
<namePart type="family">Lim</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>We introduce KFinEval, a benchmark for evaluating large language models (LLMs) in the Korean financial domain, with about 1K expert-curated instances across foundational financial knowledge, regulation-grounded procedural reasoning under noisy contexts, and financial toxicity under adversarial prompts. Existing financial benchmarks are largely English-centric and emphasize numerical or surface reasoning, providing limited coverage of regulation-grounded decision-making and domain-specific safety. Evaluating proprietary and open-weight LLMs, we observe substantial disparities and trade-offs among knowledge accuracy, procedural reasoning, and safety-aligned behavior; notably, strong capability does not consistently translate into safer responses under adversarial financial scenarios. KFinEval provides a practical Korean-regulation-grounded benchmark for diagnosing and improving financial LLM reliability and safety. Code and resources: https://github.com/sklim84/KFinEval.</abstract>
<identifier type="citekey">lim-etal-2026-kfineval</identifier>
<location>
<url>https://aclanthology.org/2026.findings-emnlp.286/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>6049</start>
<end>6081</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T KFinEval: A Curated Benchmark Suite for Real-World Korean Financial Language Understanding
%A Lim, Seonkyu
%A Hwang, Bokwang
%A Baek, Jonghyuk
%A Kim, Jingu
%A Yoo, Hangyeol
%A Lim, KyungTae
%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 lim-etal-2026-kfineval
%X We introduce KFinEval, a benchmark for evaluating large language models (LLMs) in the Korean financial domain, with about 1K expert-curated instances across foundational financial knowledge, regulation-grounded procedural reasoning under noisy contexts, and financial toxicity under adversarial prompts. Existing financial benchmarks are largely English-centric and emphasize numerical or surface reasoning, providing limited coverage of regulation-grounded decision-making and domain-specific safety. Evaluating proprietary and open-weight LLMs, we observe substantial disparities and trade-offs among knowledge accuracy, procedural reasoning, and safety-aligned behavior; notably, strong capability does not consistently translate into safer responses under adversarial financial scenarios. KFinEval provides a practical Korean-regulation-grounded benchmark for diagnosing and improving financial LLM reliability and safety. Code and resources: https://github.com/sklim84/KFinEval.
%U https://aclanthology.org/2026.findings-emnlp.286/
%P 6049-6081
Markdown (Informal)
[KFinEval: A Curated Benchmark Suite for Real-World Korean Financial Language Understanding](https://aclanthology.org/2026.findings-emnlp.286/) (Lim et al., Findings 2026)
ACL