@inproceedings{bohacek-bravansky-2024-xgboost,
title = "When {XGB}oost Outperforms {GPT}-4 on Text Classification: A Case Study",
author = "Bohacek, Matyas and
Bravansky, Michal",
editor = "Ovalle, Anaelia and
Chang, Kai-Wei and
Cao, Yang Trista and
Mehrabi, Ninareh and
Zhao, Jieyu and
Galstyan, Aram and
Dhamala, Jwala and
Kumar, Anoop and
Gupta, Rahul",
booktitle = "Proceedings of the 4th Workshop on Trustworthy Natural Language Processing (TrustNLP 2024)",
month = jun,
year = "2024",
address = "Mexico City, Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.trustnlp-1.5/",
doi = "10.18653/v1/2024.trustnlp-1.5",
pages = "51--60",
abstract = "Large language models (LLMs) are increasingly used for applications beyond text generation, ranging from text summarization to instruction following. One popular example of exploiting LLMs' zero- and few-shot capabilities is the task of text classification. This short paper compares two popular LLM-based classification pipelines (GPT-4 and LLAMA 2) to a popular pre-LLM-era classification pipeline on the task of news trustworthiness classification, focusing on performance, training, and deployment requirements. We find that, in this case, the pre-LLM-era ensemble pipeline outperforms the two popular LLM pipelines while being orders of magnitude smaller in parameter size."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bohacek-bravansky-2024-xgboost">
<titleInfo>
<title>When XGBoost Outperforms GPT-4 on Text Classification: A Case Study</title>
</titleInfo>
<name type="personal">
<namePart type="given">Matyas</namePart>
<namePart type="family">Bohacek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Michal</namePart>
<namePart type="family">Bravansky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 4th Workshop on Trustworthy Natural Language Processing (TrustNLP 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anaelia</namePart>
<namePart type="family">Ovalle</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kai-Wei</namePart>
<namePart type="family">Chang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yang</namePart>
<namePart type="given">Trista</namePart>
<namePart type="family">Cao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ninareh</namePart>
<namePart type="family">Mehrabi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jieyu</namePart>
<namePart type="family">Zhao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aram</namePart>
<namePart type="family">Galstyan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jwala</namePart>
<namePart type="family">Dhamala</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anoop</namePart>
<namePart type="family">Kumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rahul</namePart>
<namePart type="family">Gupta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Mexico City, Mexico</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Large language models (LLMs) are increasingly used for applications beyond text generation, ranging from text summarization to instruction following. One popular example of exploiting LLMs’ zero- and few-shot capabilities is the task of text classification. This short paper compares two popular LLM-based classification pipelines (GPT-4 and LLAMA 2) to a popular pre-LLM-era classification pipeline on the task of news trustworthiness classification, focusing on performance, training, and deployment requirements. We find that, in this case, the pre-LLM-era ensemble pipeline outperforms the two popular LLM pipelines while being orders of magnitude smaller in parameter size.</abstract>
<identifier type="citekey">bohacek-bravansky-2024-xgboost</identifier>
<identifier type="doi">10.18653/v1/2024.trustnlp-1.5</identifier>
<location>
<url>https://aclanthology.org/2024.trustnlp-1.5/</url>
</location>
<part>
<date>2024-06</date>
<extent unit="page">
<start>51</start>
<end>60</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T When XGBoost Outperforms GPT-4 on Text Classification: A Case Study
%A Bohacek, Matyas
%A Bravansky, Michal
%Y Ovalle, Anaelia
%Y Chang, Kai-Wei
%Y Cao, Yang Trista
%Y Mehrabi, Ninareh
%Y Zhao, Jieyu
%Y Galstyan, Aram
%Y Dhamala, Jwala
%Y Kumar, Anoop
%Y Gupta, Rahul
%S Proceedings of the 4th Workshop on Trustworthy Natural Language Processing (TrustNLP 2024)
%D 2024
%8 June
%I Association for Computational Linguistics
%C Mexico City, Mexico
%F bohacek-bravansky-2024-xgboost
%X Large language models (LLMs) are increasingly used for applications beyond text generation, ranging from text summarization to instruction following. One popular example of exploiting LLMs’ zero- and few-shot capabilities is the task of text classification. This short paper compares two popular LLM-based classification pipelines (GPT-4 and LLAMA 2) to a popular pre-LLM-era classification pipeline on the task of news trustworthiness classification, focusing on performance, training, and deployment requirements. We find that, in this case, the pre-LLM-era ensemble pipeline outperforms the two popular LLM pipelines while being orders of magnitude smaller in parameter size.
%R 10.18653/v1/2024.trustnlp-1.5
%U https://aclanthology.org/2024.trustnlp-1.5/
%U https://doi.org/10.18653/v1/2024.trustnlp-1.5
%P 51-60
Markdown (Informal)
[When XGBoost Outperforms GPT-4 on Text Classification: A Case Study](https://aclanthology.org/2024.trustnlp-1.5/) (Bohacek & Bravansky, TrustNLP 2024)
ACL