<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="peskine-etal-2023-definitions">
    <titleInfo>
        <title>Definitions Matter: Guiding GPT for Multi-label Classification</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Youri</namePart>
        <namePart type="family">Peskine</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Damir</namePart>
        <namePart type="family">Korenčić</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Ivan</namePart>
        <namePart type="family">Grubisic</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Paolo</namePart>
        <namePart type="family">Papotti</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Raphael</namePart>
        <namePart type="family">Troncy</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Paolo</namePart>
        <namePart type="family">Rosso</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2023-12</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Findings of the Association for Computational Linguistics: EMNLP 2023</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Houda</namePart>
            <namePart type="family">Bouamor</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Juan</namePart>
            <namePart type="family">Pino</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Kalika</namePart>
            <namePart type="family">Bali</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Singapore</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Large language models have recently risen in popularity due to their ability to perform many natural language tasks without requiring any fine-tuning. In this work, we focus on two novel ideas: (1) generating definitions from examples and using them for zero-shot classification, and (2) investigating how an LLM makes use of the definitions. We thoroughly analyze the performance of GPT-3 model for fine-grained multi-label conspiracy theory classification of tweets using zero-shot labeling. In doing so, we asses how to improve the labeling by providing minimal but meaningful context in the form of the definitions of the labels. We compare descriptive noun phrases, human-crafted definitions, introduce a new method to help the model generate definitions from examples, and propose a method to evaluate GPT-3’s understanding of the definitions. We demonstrate that improving definitions of class labels has a direct consequence on the downstream classification results.</abstract>
    <identifier type="citekey">peskine-etal-2023-definitions</identifier>
    <identifier type="doi">10.18653/v1/2023.findings-emnlp.267</identifier>
    <location>
        <url>https://aclanthology.org/2023.findings-emnlp.267</url>
    </location>
    <part>
        <date>2023-12</date>
        <extent unit="page">
            <start>4054</start>
            <end>4063</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Definitions Matter: Guiding GPT for Multi-label Classification
%A Peskine, Youri
%A Korenčić, Damir
%A Grubisic, Ivan
%A Papotti, Paolo
%A Troncy, Raphael
%A Rosso, Paolo
%Y Bouamor, Houda
%Y Pino, Juan
%Y Bali, Kalika
%S Findings of the Association for Computational Linguistics: EMNLP 2023
%D 2023
%8 December
%I Association for Computational Linguistics
%C Singapore
%F peskine-etal-2023-definitions
%X Large language models have recently risen in popularity due to their ability to perform many natural language tasks without requiring any fine-tuning. In this work, we focus on two novel ideas: (1) generating definitions from examples and using them for zero-shot classification, and (2) investigating how an LLM makes use of the definitions. We thoroughly analyze the performance of GPT-3 model for fine-grained multi-label conspiracy theory classification of tweets using zero-shot labeling. In doing so, we asses how to improve the labeling by providing minimal but meaningful context in the form of the definitions of the labels. We compare descriptive noun phrases, human-crafted definitions, introduce a new method to help the model generate definitions from examples, and propose a method to evaluate GPT-3’s understanding of the definitions. We demonstrate that improving definitions of class labels has a direct consequence on the downstream classification results.
%R 10.18653/v1/2023.findings-emnlp.267
%U https://aclanthology.org/2023.findings-emnlp.267
%U https://doi.org/10.18653/v1/2023.findings-emnlp.267
%P 4054-4063

Markdown (Informal)

[Definitions Matter: Guiding GPT for Multi-label Classification](https://aclanthology.org/2023.findings-emnlp.267) (Peskine et al., Findings 2023)

• Definitions Matter: Guiding GPT for Multi-label Classification (Peskine et al., Findings 2023)

ACL

• Youri Peskine, Damir Korenčić, Ivan Grubisic, Paolo Papotti, Raphael Troncy, and Paolo Rosso. 2023. Definitions Matter: Guiding GPT for Multi-label Classification. In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 4054–4063, Singapore. Association for Computational Linguistics.