CoCoP: Enhancing Text Classification with LLM through Code Completion Prompt Article Swipe

PDF

Morteza Mohajeri , Mohammad Javad Dousti , Majid Nili Ahmadabadi ·

YOU? · · 2024 · Open Access · · DOI: https://doi.org/10.48550/arxiv.2411.08979

Text classification is a fundamental task in natural language processing (NLP), and large language models (LLMs) have demonstrated their capability to perform this task across various domains. However, the performance of LLMs heavily depends on the quality of their input prompts. Recent studies have also shown that LLMs exhibit remarkable results in code-related tasks. To leverage the capabilities of LLMs in text classification, we propose the Code Completion Prompt (CoCoP) method, which transforms the text classification problem into a code completion task. CoCoP significantly improves text classification performance across diverse datasets by utilizing LLMs' code-completion capability. For instance, CoCoP enhances the accuracy of the SST2 dataset by more than 20%. Moreover, when CoCoP integrated with LLMs specifically designed for code-related tasks (code models), such as CodeLLaMA, this method demonstrates better or comparable performance to few-shot learning techniques while using only one-tenth of the model size. The source code of our proposed method will be available to the public upon the acceptance of the paper.

Related Topics

Computer Science

Artificial Intelligence

Programming Language

Concepts

Code (set theory) Computer science Natural language processing Artificial intelligence Programming language Set (abstract data type)

Metadata

Type: preprint
Language: en
Landing Page: http://arxiv.org/abs/2411.08979
PDF: https://arxiv.org/pdf/2411.08979
OA Status: green
Related Works: 10
OpenAlex ID: https://openalex.org/W4404449844

All OpenAlex metadata

Raw OpenAlex JSON

OpenAlex ID: https://openalex.org/W4404449844

Canonical identifier for this work in OpenAlex
DOI: https://doi.org/10.48550/arxiv.2411.08979

Digital Object Identifier
Title: CoCoP: Enhancing Text Classification with LLM through Code Completion Prompt

Work title
Type: preprint

OpenAlex work type
Language: en

Primary language
Publication year: 2024

Year of publication
Publication date: 2024-11-13

Full publication date if available
Authors: Morteza Mohajeri, Mohammad Javad Dousti, Majid Nili Ahmadabadi

List of authors in order
Landing page: https://arxiv.org/abs/2411.08979

Publisher landing page
PDF URL: https://arxiv.org/pdf/2411.08979

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/2411.08979

Direct OA link when available
Concepts: Code (set theory), Computer science, Natural language processing, Artificial intelligence, Programming language, Set (abstract data type)

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/W4404449844
doi	https://doi.org/10.48550/arxiv.2411.08979
ids.doi	https://doi.org/10.48550/arxiv.2411.08979
ids.openalex	https://openalex.org/W4404449844
fwci
type	preprint
title	CoCoP: Enhancing Text Classification with LLM through Code Completion Prompt
biblio.issue
biblio.volume
biblio.last_page
biblio.first_page
topics[0].id	https://openalex.org/T10181
topics[0].field.id	https://openalex.org/fields/17
topics[0].field.display_name	Computer Science
topics[0].score	0.9764000177383423
topics[0].domain.id	https://openalex.org/domains/3
topics[0].domain.display_name	Physical Sciences
topics[0].subfield.id	https://openalex.org/subfields/1702
topics[0].subfield.display_name	Artificial Intelligence
topics[0].display_name	Natural Language Processing Techniques
is_xpac	False
apc_list
apc_paid
concepts[0].id	https://openalex.org/C2776760102
concepts[0].level	3
concepts[0].score	0.614967942237854
concepts[0].wikidata	https://www.wikidata.org/wiki/Q5139990
concepts[0].display_name	Code (set theory)
concepts[1].id	https://openalex.org/C41008148
concepts[1].level	0
concepts[1].score	0.5257022380828857
concepts[1].wikidata	https://www.wikidata.org/wiki/Q21198
concepts[1].display_name	Computer science
concepts[2].id	https://openalex.org/C204321447
concepts[2].level	1
concepts[2].score	0.4783715307712555
concepts[2].wikidata	https://www.wikidata.org/wiki/Q30642
concepts[2].display_name	Natural language processing
concepts[3].id	https://openalex.org/C154945302
concepts[3].level	1
concepts[3].score	0.3396109342575073
concepts[3].wikidata	https://www.wikidata.org/wiki/Q11660
concepts[3].display_name	Artificial intelligence
concepts[4].id	https://openalex.org/C199360897
concepts[4].level	1
concepts[4].score	0.28520667552948
concepts[4].wikidata	https://www.wikidata.org/wiki/Q9143
concepts[4].display_name	Programming language
concepts[5].id	https://openalex.org/C177264268
concepts[5].level	2
concepts[5].score	0.0
concepts[5].wikidata	https://www.wikidata.org/wiki/Q1514741
concepts[5].display_name	Set (abstract data type)
keywords[0].id	https://openalex.org/keywords/code
keywords[0].score	0.614967942237854
keywords[0].display_name	Code (set theory)
keywords[1].id	https://openalex.org/keywords/computer-science
keywords[1].score	0.5257022380828857
keywords[1].display_name	Computer science
keywords[2].id	https://openalex.org/keywords/natural-language-processing
keywords[2].score	0.4783715307712555
keywords[2].display_name	Natural language processing
keywords[3].id	https://openalex.org/keywords/artificial-intelligence
keywords[3].score	0.3396109342575073
keywords[3].display_name	Artificial intelligence
keywords[4].id	https://openalex.org/keywords/programming-language
keywords[4].score	0.28520667552948
keywords[4].display_name	Programming language
language	en
locations[0].id	pmh:oai:arXiv.org:2411.08979
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/2411.08979
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/2411.08979
locations[1].id	doi:10.48550/arxiv.2411.08979
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.2411.08979
indexed_in	arxiv, datacite
authorships[0].author.id	https://openalex.org/A5029861583
authorships[0].author.orcid
authorships[0].author.display_name	Morteza Mohajeri
authorships[0].author_position	first
authorships[0].raw_author_name	Mohajeri, Mohammad Mahdi
authorships[0].is_corresponding	False
authorships[1].author.id	https://openalex.org/A5001927789
authorships[1].author.orcid	https://orcid.org/0000-0002-8537-2916
authorships[1].author.display_name	Mohammad Javad Dousti
authorships[1].author_position	middle
authorships[1].raw_author_name	Dousti, Mohammad Javad
authorships[1].is_corresponding	False
authorships[2].author.id	https://openalex.org/A5072135442
authorships[2].author.orcid	https://orcid.org/0000-0002-6370-6057
authorships[2].author.display_name	Majid Nili Ahmadabadi
authorships[2].author_position	last
authorships[2].raw_author_name	Ahmadabadi, Majid Nili
authorships[2].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/2411.08979
open_access.oa_status	green
open_access.any_repository_has_fulltext	False
created_date	2025-10-10T00:00:00
display_name	CoCoP: Enhancing Text Classification with LLM through Code Completion Prompt
has_fulltext	False
is_retracted	False
updated_date	2025-11-06T06:51:31.235846
primary_topic.id	https://openalex.org/T10181
primary_topic.field.id	https://openalex.org/fields/17
primary_topic.field.display_name	Computer Science
primary_topic.score	0.9764000177383423
primary_topic.domain.id	https://openalex.org/domains/3
primary_topic.domain.display_name	Physical Sciences
primary_topic.subfield.id	https://openalex.org/subfields/1702
primary_topic.subfield.display_name	Artificial Intelligence
primary_topic.display_name	Natural Language Processing Techniques
related_works	https://openalex.org/W4391375266, https://openalex.org/W2899084033, https://openalex.org/W2748952813, https://openalex.org/W2390279801, https://openalex.org/W4391913857, https://openalex.org/W2358668433, https://openalex.org/W4396701345, https://openalex.org/W2376932109, https://openalex.org/W2001405890, https://openalex.org/W3204019825
cited_by_count	0
locations_count	2
best_oa_location.id	pmh:oai:arXiv.org:2411.08979
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/2411.08979
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/2411.08979
primary_location.id	pmh:oai:arXiv.org:2411.08979
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/2411.08979
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/2411.08979
publication_date	2024-11-13
publication_year	2024
referenced_works_count	0
abstract_inverted_index.a	3, 78
abstract_inverted_index.To	54
abstract_inverted_index.as	124
abstract_inverted_index.be	153
abstract_inverted_index.by	91, 106
abstract_inverted_index.in	6, 51, 60
abstract_inverted_index.is	2
abstract_inverted_index.of	30, 37, 58, 102, 141, 148, 161
abstract_inverted_index.on	34
abstract_inverted_index.or	130
abstract_inverted_index.to	20, 133, 155
abstract_inverted_index.we	63
abstract_inverted_index.For	96
abstract_inverted_index.The	145
abstract_inverted_index.and	11
abstract_inverted_index.for	118
abstract_inverted_index.our	149
abstract_inverted_index.the	28, 35, 56, 65, 73, 100, 103, 142, 156, 159, 162
abstract_inverted_index.20%.	109
abstract_inverted_index.Code	66
abstract_inverted_index.LLMs	31, 47, 59, 115
abstract_inverted_index.SST2	104
abstract_inverted_index.Text	0
abstract_inverted_index.also	44
abstract_inverted_index.code	79, 147
abstract_inverted_index.have	16, 43
abstract_inverted_index.into	77
abstract_inverted_index.more	107
abstract_inverted_index.only	139
abstract_inverted_index.such	123
abstract_inverted_index.task	5, 23
abstract_inverted_index.text	61, 74, 85
abstract_inverted_index.than	108
abstract_inverted_index.that	46
abstract_inverted_index.this	22, 126
abstract_inverted_index.upon	158
abstract_inverted_index.when	111
abstract_inverted_index.will	152
abstract_inverted_index.with	114
abstract_inverted_index.(code	121
abstract_inverted_index.CoCoP	82, 98, 112
abstract_inverted_index.LLMs'	93
abstract_inverted_index.input	39
abstract_inverted_index.large	12
abstract_inverted_index.model	143
abstract_inverted_index.shown	45
abstract_inverted_index.size.	144
abstract_inverted_index.task.	81
abstract_inverted_index.tasks	120
abstract_inverted_index.their	18, 38
abstract_inverted_index.using	138
abstract_inverted_index.which	71
abstract_inverted_index.while	137
abstract_inverted_index.(LLMs)	15
abstract_inverted_index.(NLP),	10
abstract_inverted_index.Prompt	68
abstract_inverted_index.Recent	41
abstract_inverted_index.across	24, 88
abstract_inverted_index.better	129
abstract_inverted_index.method	127, 151
abstract_inverted_index.models	14
abstract_inverted_index.paper.	163
abstract_inverted_index.public	157
abstract_inverted_index.source	146
abstract_inverted_index.tasks.	53
abstract_inverted_index.(CoCoP)	69
abstract_inverted_index.dataset	105
abstract_inverted_index.depends	33
abstract_inverted_index.diverse	89
abstract_inverted_index.exhibit	48
abstract_inverted_index.heavily	32
abstract_inverted_index.method,	70
abstract_inverted_index.natural	7
abstract_inverted_index.perform	21
abstract_inverted_index.problem	76
abstract_inverted_index.propose	64
abstract_inverted_index.quality	36
abstract_inverted_index.results	50
abstract_inverted_index.studies	42
abstract_inverted_index.various	25
abstract_inverted_index.However,	27
abstract_inverted_index.accuracy	101
abstract_inverted_index.datasets	90
abstract_inverted_index.designed	117
abstract_inverted_index.domains.	26
abstract_inverted_index.enhances	99
abstract_inverted_index.few-shot	134
abstract_inverted_index.improves	84
abstract_inverted_index.language	8, 13
abstract_inverted_index.learning	135
abstract_inverted_index.leverage	55
abstract_inverted_index.models),	122
abstract_inverted_index.prompts.	40
abstract_inverted_index.proposed	150
abstract_inverted_index.Moreover,	110
abstract_inverted_index.available	154
abstract_inverted_index.instance,	97
abstract_inverted_index.one-tenth	140
abstract_inverted_index.utilizing	92
abstract_inverted_index.CodeLLaMA,	125
abstract_inverted_index.Completion	67
abstract_inverted_index.acceptance	160
abstract_inverted_index.capability	19
abstract_inverted_index.comparable	131
abstract_inverted_index.completion	80
abstract_inverted_index.integrated	113
abstract_inverted_index.processing	9
abstract_inverted_index.remarkable	49
abstract_inverted_index.techniques	136
abstract_inverted_index.transforms	72
abstract_inverted_index.capability.	95
abstract_inverted_index.fundamental	4
abstract_inverted_index.performance	29, 87, 132
abstract_inverted_index.capabilities	57
abstract_inverted_index.code-related	52, 119
abstract_inverted_index.demonstrated	17
abstract_inverted_index.demonstrates	128
abstract_inverted_index.specifically	116
abstract_inverted_index.significantly	83
abstract_inverted_index.classification	1, 75, 86
abstract_inverted_index.classification,	62
abstract_inverted_index.code-completion	94
cited_by_percentile_year
countries_distinct_count	0
institutions_distinct_count	3
citation_normalized_percentile