<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="beno-2025-electra">
    <titleInfo>
        <title>ELECTRA and GPT-4o: Cost-Effective Partners for Sentiment Analysis</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">James</namePart>
        <namePart type="given">P</namePart>
        <namePart type="family">Beno</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2025-05</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 4th International Workshop on Knowledge-Augmented Methods for Natural Language Processing</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Weijia</namePart>
            <namePart type="family">Shi</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Wenhao</namePart>
            <namePart type="family">Yu</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Akari</namePart>
            <namePart type="family">Asai</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Meng</namePart>
            <namePart type="family">Jiang</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Greg</namePart>
            <namePart type="family">Durrett</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Hannaneh</namePart>
            <namePart type="family">Hajishirzi</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Luke</namePart>
            <namePart type="family">Zettlemoyer</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Albuquerque, New Mexico, USA</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-229-9</identifier>
    </relatedItem>
    <abstract>Bidirectional transformers excel at sentiment analysis, and Large Language Models (LLM) are effective zero-shot learners. Might they perform better as a team? This paper explores collaborative approaches between ELECTRA and GPT-4o for three-way sentiment classification. We fine-tuned (FT) four models (ELECTRA Base/Large, GPT-4o/4o-mini) using a mix of reviews from Stanford Sentiment Treebank (SST) and DynaSent. We provided input from ELECTRA to GPT as: predicted label, probabilities, and retrieved examples. Sharing ELECTRA Base FT predictions with GPT-4o-mini significantly improved performance over either model alone (82.50 macro F1 vs. 79.14 ELECTRA Base FT, 79.41 GPT-4o-mini) and yielded the lowest cost/performance ratio ($0.12/F1 point). However, when GPT models were fine-tuned, including predictions decreased performance. GPT-4o FT-M was the top performer (86.99), with GPT-4o-mini FT close behind (86.70) at much less cost ($0.38 vs. $1.59/F1 point). Our results show that augmenting prompts with predictions from fine-tuned encoders is an efficient way to boost performance, and a fine-tuned GPT-4o-mini is nearly as good as GPT-4o FT at 76% less cost. Both are affordable options for projects with limited resources.</abstract>
    <identifier type="citekey">beno-2025-electra</identifier>
    <identifier type="doi">10.18653/v1/2025.knowledgenlp-1.2</identifier>
    <location>
        <url>https://aclanthology.org/2025.knowledgenlp-1.2/</url>
    </location>
    <part>
        <date>2025-05</date>
        <extent unit="page">
            <start>18</start>
            <end>36</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T ELECTRA and GPT-4o: Cost-Effective Partners for Sentiment Analysis
%A Beno, James P.
%Y Shi, Weijia
%Y Yu, Wenhao
%Y Asai, Akari
%Y Jiang, Meng
%Y Durrett, Greg
%Y Hajishirzi, Hannaneh
%Y Zettlemoyer, Luke
%S Proceedings of the 4th International Workshop on Knowledge-Augmented Methods for Natural Language Processing
%D 2025
%8 May
%I Association for Computational Linguistics
%C Albuquerque, New Mexico, USA
%@ 979-8-89176-229-9
%F beno-2025-electra
%X Bidirectional transformers excel at sentiment analysis, and Large Language Models (LLM) are effective zero-shot learners. Might they perform better as a team? This paper explores collaborative approaches between ELECTRA and GPT-4o for three-way sentiment classification. We fine-tuned (FT) four models (ELECTRA Base/Large, GPT-4o/4o-mini) using a mix of reviews from Stanford Sentiment Treebank (SST) and DynaSent. We provided input from ELECTRA to GPT as: predicted label, probabilities, and retrieved examples. Sharing ELECTRA Base FT predictions with GPT-4o-mini significantly improved performance over either model alone (82.50 macro F1 vs. 79.14 ELECTRA Base FT, 79.41 GPT-4o-mini) and yielded the lowest cost/performance ratio ($0.12/F1 point). However, when GPT models were fine-tuned, including predictions decreased performance. GPT-4o FT-M was the top performer (86.99), with GPT-4o-mini FT close behind (86.70) at much less cost ($0.38 vs. $1.59/F1 point). Our results show that augmenting prompts with predictions from fine-tuned encoders is an efficient way to boost performance, and a fine-tuned GPT-4o-mini is nearly as good as GPT-4o FT at 76% less cost. Both are affordable options for projects with limited resources.
%R 10.18653/v1/2025.knowledgenlp-1.2
%U https://aclanthology.org/2025.knowledgenlp-1.2/
%U https://doi.org/10.18653/v1/2025.knowledgenlp-1.2
%P 18-36

Markdown (Informal)

[ELECTRA and GPT-4o: Cost-Effective Partners for Sentiment Analysis](https://aclanthology.org/2025.knowledgenlp-1.2/) (Beno, KnowledgeNLP 2025)

• ELECTRA and GPT-4o: Cost-Effective Partners for Sentiment Analysis (Beno, KnowledgeNLP 2025)

ACL

• James P. Beno. 2025. ELECTRA and GPT-4o: Cost-Effective Partners for Sentiment Analysis. In Proceedings of the 4th International Workshop on Knowledge-Augmented Methods for Natural Language Processing, pages 18–36, Albuquerque, New Mexico, USA. Association for Computational Linguistics.