TWICE: What Advantages Can Low-Resource Domain-Specific Embedding Model Bring? -- A Case Study on Korea Financial Texts Article Swipe

PDF

Y. S. Hwang , Sung Jun Jung , Hanwool Lee , Shui Yu ·

YOU? · · 2025 · Open Access · · DOI: https://doi.org/10.48550/arxiv.2502.07131

Domain specificity of embedding models is critical for effective performance. However, existing benchmarks, such as FinMTEB, are primarily designed for high-resource languages, leaving low-resource settings, such as Korean, under-explored. Directly translating established English benchmarks often fails to capture the linguistic and cultural nuances present in low-resource domains. In this paper, titled TWICE: What Advantages Can Low-Resource Domain-Specific Embedding Models Bring? A Case Study on Korea Financial Texts, we introduce KorFinMTEB, a novel benchmark for the Korean financial domain, specifically tailored to reflect its unique cultural characteristics in low-resource languages. Our experimental results reveal that while the models perform robustly on a translated version of FinMTEB, their performance on KorFinMTEB uncovers subtle yet critical discrepancies, especially in tasks requiring deeper semantic understanding, that underscore the limitations of direct translation. This discrepancy highlights the necessity of benchmarks that incorporate language-specific idiosyncrasies and cultural nuances. The insights from our study advocate for the development of domain-specific evaluation frameworks that can more accurately assess and drive the progress of embedding models in low-resource settings.

Related Topics

Business

Finance

Computer Science

Artificial Intelligence

Mathematics

Mathematical Analysis

Concepts

Embedding Business Domain (mathematical analysis) Resource (disambiguation) Finance Computer science Artificial intelligence Mathematics Mathematical analysis Computer network

Metadata

Type: preprint
Language: en
Landing Page: http://arxiv.org/abs/2502.07131
PDF: https://arxiv.org/pdf/2502.07131
OA Status: green
Related Works: 10
OpenAlex ID: https://openalex.org/W4407424101

All OpenAlex metadata

Raw OpenAlex JSON

OpenAlex ID: https://openalex.org/W4407424101

Canonical identifier for this work in OpenAlex
DOI: https://doi.org/10.48550/arxiv.2502.07131

Digital Object Identifier
Title: TWICE: What Advantages Can Low-Resource Domain-Specific Embedding Model Bring? -- A Case Study on Korea Financial Texts

Work title
Type: preprint

OpenAlex work type
Language: en

Primary language
Publication year: 2025

Year of publication
Publication date: 2025-02-10

Full publication date if available
Authors: Y. S. Hwang, Sung Jun Jung, Hanwool Lee, Shui Yu

List of authors in order
Landing page: https://arxiv.org/abs/2502.07131

Publisher landing page
PDF URL: https://arxiv.org/pdf/2502.07131

Direct link to full text PDF
Open access: Yes

Whether a free full text is available
OA status: green

Open access status per OpenAlex
OA URL: https://arxiv.org/pdf/2502.07131

Direct OA link when available
Concepts: Embedding, Business, Domain (mathematical analysis), Resource (disambiguation), Finance, Computer science, Artificial intelligence, Mathematics, Mathematical analysis, Computer network

Top concepts (fields/topics) attached by OpenAlex
Cited by: 0

Total citation count in OpenAlex
Related works (count): 10

Other works algorithmically related by OpenAlex

Full payload

id	https://openalex.org/W4407424101
doi	https://doi.org/10.48550/arxiv.2502.07131
ids.doi	https://doi.org/10.48550/arxiv.2502.07131
ids.openalex	https://openalex.org/W4407424101
fwci
type	preprint
title	TWICE: What Advantages Can Low-Resource Domain-Specific Embedding Model Bring? -- A Case Study on Korea Financial Texts
biblio.issue
biblio.volume
biblio.last_page
biblio.first_page
topics[0].id	https://openalex.org/T14419
topics[0].field.id	https://openalex.org/fields/14
topics[0].field.display_name	Business, Management and Accounting
topics[0].score	0.6665999889373779
topics[0].domain.id	https://openalex.org/domains/2
topics[0].domain.display_name	Social Sciences
topics[0].subfield.id	https://openalex.org/subfields/1402
topics[0].subfield.display_name	Accounting
topics[0].display_name	Banking Systems and Strategies
is_xpac	False
apc_list
apc_paid
concepts[0].id	https://openalex.org/C41608201
concepts[0].level	2
concepts[0].score	0.6126416921615601
concepts[0].wikidata	https://www.wikidata.org/wiki/Q980509
concepts[0].display_name	Embedding
concepts[1].id	https://openalex.org/C144133560
concepts[1].level	0
concepts[1].score	0.5170627236366272
concepts[1].wikidata	https://www.wikidata.org/wiki/Q4830453
concepts[1].display_name	Business
concepts[2].id	https://openalex.org/C36503486
concepts[2].level	2
concepts[2].score	0.48625099658966064
concepts[2].wikidata	https://www.wikidata.org/wiki/Q11235244
concepts[2].display_name	Domain (mathematical analysis)
concepts[3].id	https://openalex.org/C206345919
concepts[3].level	2
concepts[3].score	0.4177986979484558
concepts[3].wikidata	https://www.wikidata.org/wiki/Q20380951
concepts[3].display_name	Resource (disambiguation)
concepts[4].id	https://openalex.org/C10138342
concepts[4].level	1
concepts[4].score	0.3774470090866089
concepts[4].wikidata	https://www.wikidata.org/wiki/Q43015
concepts[4].display_name	Finance
concepts[5].id	https://openalex.org/C41008148
concepts[5].level	0
concepts[5].score	0.3443799316883087
concepts[5].wikidata	https://www.wikidata.org/wiki/Q21198
concepts[5].display_name	Computer science
concepts[6].id	https://openalex.org/C154945302
concepts[6].level	1
concepts[6].score	0.14510813355445862
concepts[6].wikidata	https://www.wikidata.org/wiki/Q11660
concepts[6].display_name	Artificial intelligence
concepts[7].id	https://openalex.org/C33923547
concepts[7].level	0
concepts[7].score	0.11742493510246277
concepts[7].wikidata	https://www.wikidata.org/wiki/Q395
concepts[7].display_name	Mathematics
concepts[8].id	https://openalex.org/C134306372
concepts[8].level	1
concepts[8].score	0.0
concepts[8].wikidata	https://www.wikidata.org/wiki/Q7754
concepts[8].display_name	Mathematical analysis
concepts[9].id	https://openalex.org/C31258907
concepts[9].level	1
concepts[9].score	0.0
concepts[9].wikidata	https://www.wikidata.org/wiki/Q1301371
concepts[9].display_name	Computer network
keywords[0].id	https://openalex.org/keywords/embedding
keywords[0].score	0.6126416921615601
keywords[0].display_name	Embedding
keywords[1].id	https://openalex.org/keywords/business
keywords[1].score	0.5170627236366272
keywords[1].display_name	Business
keywords[2].id	https://openalex.org/keywords/domain
keywords[2].score	0.48625099658966064
keywords[2].display_name	Domain (mathematical analysis)
keywords[3].id	https://openalex.org/keywords/resource
keywords[3].score	0.4177986979484558
keywords[3].display_name	Resource (disambiguation)
keywords[4].id	https://openalex.org/keywords/finance
keywords[4].score	0.3774470090866089
keywords[4].display_name	Finance
keywords[5].id	https://openalex.org/keywords/computer-science
keywords[5].score	0.3443799316883087
keywords[5].display_name	Computer science
keywords[6].id	https://openalex.org/keywords/artificial-intelligence
keywords[6].score	0.14510813355445862
keywords[6].display_name	Artificial intelligence
keywords[7].id	https://openalex.org/keywords/mathematics
keywords[7].score	0.11742493510246277
keywords[7].display_name	Mathematics
language	en
locations[0].id	pmh:oai:arXiv.org:2502.07131
locations[0].is_oa	True
locations[0].source.id	https://openalex.org/S4306400194
locations[0].source.issn
locations[0].source.type	repository
locations[0].source.is_oa	True
locations[0].source.issn_l
locations[0].source.is_core	False
locations[0].source.is_in_doaj	False
locations[0].source.display_name	arXiv (Cornell University)
locations[0].source.host_organization	https://openalex.org/I205783295
locations[0].source.host_organization_name	Cornell University
locations[0].source.host_organization_lineage	https://openalex.org/I205783295
locations[0].license
locations[0].pdf_url	https://arxiv.org/pdf/2502.07131
locations[0].version	submittedVersion
locations[0].raw_type	text
locations[0].license_id
locations[0].is_accepted	False
locations[0].is_published	False
locations[0].raw_source_name
locations[0].landing_page_url	http://arxiv.org/abs/2502.07131
locations[1].id	doi:10.48550/arxiv.2502.07131
locations[1].is_oa	True
locations[1].source.id	https://openalex.org/S4306400194
locations[1].source.issn
locations[1].source.type	repository
locations[1].source.is_oa	True
locations[1].source.issn_l
locations[1].source.is_core	False
locations[1].source.is_in_doaj	False
locations[1].source.display_name	arXiv (Cornell University)
locations[1].source.host_organization	https://openalex.org/I205783295
locations[1].source.host_organization_name	Cornell University
locations[1].source.host_organization_lineage	https://openalex.org/I205783295
locations[1].license
locations[1].pdf_url
locations[1].version
locations[1].raw_type	article
locations[1].license_id
locations[1].is_accepted	False
locations[1].is_published
locations[1].raw_source_name
locations[1].landing_page_url	https://doi.org/10.48550/arxiv.2502.07131
indexed_in	arxiv, datacite
authorships[0].author.id	https://openalex.org/A5073016636
authorships[0].author.orcid	https://orcid.org/0000-0002-4010-9241
authorships[0].author.display_name	Y. S. Hwang
authorships[0].author_position	first
authorships[0].raw_author_name	Hwang, Yewon
authorships[0].is_corresponding	False
authorships[1].author.id	https://openalex.org/A5041517590
authorships[1].author.orcid	https://orcid.org/0000-0002-1051-6495
authorships[1].author.display_name	Sung Jun Jung
authorships[1].author_position	middle
authorships[1].raw_author_name	Jung, Sungbum
authorships[1].is_corresponding	False
authorships[2].author.id	https://openalex.org/A5103110871
authorships[2].author.orcid	https://orcid.org/0000-0001-5565-5184
authorships[2].author.display_name	Hanwool Lee
authorships[2].author_position	middle
authorships[2].raw_author_name	Lee, Hanwool
authorships[2].is_corresponding	False
authorships[3].author.id	https://openalex.org/A5005228053
authorships[3].author.orcid	https://orcid.org/0000-0003-4485-6743
authorships[3].author.display_name	Shui Yu
authorships[3].author_position	last
authorships[3].raw_author_name	Yu, Sara
authorships[3].is_corresponding	False
has_content.pdf	False
has_content.grobid_xml	False
is_paratext	False
open_access.is_oa	True
open_access.oa_url	https://arxiv.org/pdf/2502.07131
open_access.oa_status	green
open_access.any_repository_has_fulltext	False
created_date	2025-10-10T00:00:00
display_name	TWICE: What Advantages Can Low-Resource Domain-Specific Embedding Model Bring? -- A Case Study on Korea Financial Texts
has_fulltext	False
is_retracted	False
updated_date	2025-11-06T06:51:31.235846
primary_topic.id	https://openalex.org/T14419
primary_topic.field.id	https://openalex.org/fields/14
primary_topic.field.display_name	Business, Management and Accounting
primary_topic.score	0.6665999889373779
primary_topic.domain.id	https://openalex.org/domains/2
primary_topic.domain.display_name	Social Sciences
primary_topic.subfield.id	https://openalex.org/subfields/1402
primary_topic.subfield.display_name	Accounting
primary_topic.display_name	Banking Systems and Strategies
related_works	https://openalex.org/W4391375266, https://openalex.org/W2081900870, https://openalex.org/W2037549926, https://openalex.org/W2345479200, https://openalex.org/W2183306018, https://openalex.org/W2849310602, https://openalex.org/W3006008237, https://openalex.org/W2419146053, https://openalex.org/W4388890789, https://openalex.org/W2088247287
cited_by_count	0
locations_count	2
best_oa_location.id	pmh:oai:arXiv.org:2502.07131
best_oa_location.is_oa	True
best_oa_location.source.id	https://openalex.org/S4306400194
best_oa_location.source.issn
best_oa_location.source.type	repository
best_oa_location.source.is_oa	True
best_oa_location.source.issn_l
best_oa_location.source.is_core	False
best_oa_location.source.is_in_doaj	False
best_oa_location.source.display_name	arXiv (Cornell University)
best_oa_location.source.host_organization	https://openalex.org/I205783295
best_oa_location.source.host_organization_name	Cornell University
best_oa_location.source.host_organization_lineage	https://openalex.org/I205783295
best_oa_location.license
best_oa_location.pdf_url	https://arxiv.org/pdf/2502.07131
best_oa_location.version	submittedVersion
best_oa_location.raw_type	text
best_oa_location.license_id
best_oa_location.is_accepted	False
best_oa_location.is_published	False
best_oa_location.raw_source_name
best_oa_location.landing_page_url	http://arxiv.org/abs/2502.07131
primary_location.id	pmh:oai:arXiv.org:2502.07131
primary_location.is_oa	True
primary_location.source.id	https://openalex.org/S4306400194
primary_location.source.issn
primary_location.source.type	repository
primary_location.source.is_oa	True
primary_location.source.issn_l
primary_location.source.is_core	False
primary_location.source.is_in_doaj	False
primary_location.source.display_name	arXiv (Cornell University)
primary_location.source.host_organization	https://openalex.org/I205783295
primary_location.source.host_organization_name	Cornell University
primary_location.source.host_organization_lineage	https://openalex.org/I205783295
primary_location.license
primary_location.pdf_url	https://arxiv.org/pdf/2502.07131
primary_location.version	submittedVersion
primary_location.raw_type	text
primary_location.license_id
primary_location.is_accepted	False
primary_location.is_published	False
primary_location.raw_source_name
primary_location.landing_page_url	http://arxiv.org/abs/2502.07131
publication_date	2025-02-10
publication_year	2025
referenced_works_count	0
abstract_inverted_index.A	60
abstract_inverted_index.a	70, 100
abstract_inverted_index.In	47
abstract_inverted_index.as	14, 26
abstract_inverted_index.in	44, 86, 115, 167
abstract_inverted_index.is	5
abstract_inverted_index.of	2, 103, 125, 133, 151, 164
abstract_inverted_index.on	63, 99, 107
abstract_inverted_index.to	36, 80
abstract_inverted_index.we	67
abstract_inverted_index.Can	54
abstract_inverted_index.Our	89
abstract_inverted_index.The	142
abstract_inverted_index.and	40, 139, 160
abstract_inverted_index.are	16
abstract_inverted_index.can	156
abstract_inverted_index.for	7, 19, 73, 148
abstract_inverted_index.its	82
abstract_inverted_index.our	145
abstract_inverted_index.the	38, 74, 95, 123, 131, 149, 162
abstract_inverted_index.yet	111
abstract_inverted_index.Case	61
abstract_inverted_index.This	128
abstract_inverted_index.What	52
abstract_inverted_index.from	144
abstract_inverted_index.more	157
abstract_inverted_index.such	13, 25
abstract_inverted_index.that	93, 121, 135, 155
abstract_inverted_index.this	48
abstract_inverted_index.Korea	64
abstract_inverted_index.Study	62
abstract_inverted_index.drive	161
abstract_inverted_index.fails	35
abstract_inverted_index.novel	71
abstract_inverted_index.often	34
abstract_inverted_index.study	146
abstract_inverted_index.tasks	116
abstract_inverted_index.their	105
abstract_inverted_index.while	94
abstract_inverted_index.Bring?	59
abstract_inverted_index.Domain	0
abstract_inverted_index.Korean	75
abstract_inverted_index.Models	58
abstract_inverted_index.TWICE:	51
abstract_inverted_index.Texts,	66
abstract_inverted_index.assess	159
abstract_inverted_index.deeper	118
abstract_inverted_index.direct	126
abstract_inverted_index.models	4, 96, 166
abstract_inverted_index.paper,	49
abstract_inverted_index.reveal	92
abstract_inverted_index.subtle	110
abstract_inverted_index.titled	50
abstract_inverted_index.unique	83
abstract_inverted_index.English	32
abstract_inverted_index.Korean,	27
abstract_inverted_index.capture	37
abstract_inverted_index.domain,	77
abstract_inverted_index.leaving	22
abstract_inverted_index.nuances	42
abstract_inverted_index.perform	97
abstract_inverted_index.present	43
abstract_inverted_index.reflect	81
abstract_inverted_index.results	91
abstract_inverted_index.version	102
abstract_inverted_index.Directly	29
abstract_inverted_index.FinMTEB,	15, 104
abstract_inverted_index.However,	10
abstract_inverted_index.advocate	147
abstract_inverted_index.critical	6, 112
abstract_inverted_index.cultural	41, 84, 140
abstract_inverted_index.designed	18
abstract_inverted_index.domains.	46
abstract_inverted_index.existing	11
abstract_inverted_index.insights	143
abstract_inverted_index.nuances.	141
abstract_inverted_index.progress	163
abstract_inverted_index.robustly	98
abstract_inverted_index.semantic	119
abstract_inverted_index.tailored	79
abstract_inverted_index.uncovers	109
abstract_inverted_index.Embedding	57
abstract_inverted_index.Financial	65
abstract_inverted_index.benchmark	72
abstract_inverted_index.effective	8
abstract_inverted_index.embedding	3, 165
abstract_inverted_index.financial	76
abstract_inverted_index.introduce	68
abstract_inverted_index.necessity	132
abstract_inverted_index.primarily	17
abstract_inverted_index.requiring	117
abstract_inverted_index.settings,	24
abstract_inverted_index.settings.	169
abstract_inverted_index.Advantages	53
abstract_inverted_index.KorFinMTEB	108
abstract_inverted_index.accurately	158
abstract_inverted_index.benchmarks	33, 134
abstract_inverted_index.especially	114
abstract_inverted_index.evaluation	153
abstract_inverted_index.frameworks	154
abstract_inverted_index.highlights	130
abstract_inverted_index.languages,	21
abstract_inverted_index.languages.	88
abstract_inverted_index.linguistic	39
abstract_inverted_index.translated	101
abstract_inverted_index.underscore	122
abstract_inverted_index.KorFinMTEB,	69
abstract_inverted_index.benchmarks,	12
abstract_inverted_index.development	150
abstract_inverted_index.discrepancy	129
abstract_inverted_index.established	31
abstract_inverted_index.incorporate	136
abstract_inverted_index.limitations	124
abstract_inverted_index.performance	106
abstract_inverted_index.specificity	1
abstract_inverted_index.translating	30
abstract_inverted_index.Low-Resource	55
abstract_inverted_index.experimental	90
abstract_inverted_index.low-resource	23, 45, 87, 168
abstract_inverted_index.performance.	9
abstract_inverted_index.specifically	78
abstract_inverted_index.translation.	127
abstract_inverted_index.high-resource	20
abstract_inverted_index.discrepancies,	113
abstract_inverted_index.idiosyncrasies	138
abstract_inverted_index.understanding,	120
abstract_inverted_index.Domain-Specific	56
abstract_inverted_index.characteristics	85
abstract_inverted_index.domain-specific	152
abstract_inverted_index.under-explored.	28
abstract_inverted_index.language-specific	137
cited_by_percentile_year
countries_distinct_count	0
institutions_distinct_count	4
citation_normalized_percentile