<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="adiga-etal-2024-designing">
    <titleInfo>
        <title>Designing Informative Metrics for Few-Shot Example Selection</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Rishabh</namePart>
        <namePart type="family">Adiga</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Lakshmi</namePart>
        <namePart type="family">Subramanian</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Varun</namePart>
        <namePart type="family">Chandrasekaran</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2024-08</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Findings of the Association for Computational Linguistics: ACL 2024</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Lun-Wei</namePart>
            <namePart type="family">Ku</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Andre</namePart>
            <namePart type="family">Martins</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Vivek</namePart>
            <namePart type="family">Srikumar</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Bangkok, Thailand</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Pretrained language models (PLMs) have shown remarkable few-shot learning capabilities when provided with properly formatted examples. However, selecting the “best” examples remains an open challenge. We propose a complexity-based prompt selection approach for sequence tagging tasks. This approach avoids the training of a dedicated model for selection of examples, and instead uses certain metrics to align the syntactico-semantic complexity of test sentences and examples. We use both sentence- and word-level metrics to match the complexity of examples to the (test) sentence being considered. Our results demonstrate that our approach extracts greater performance from PLMs: it achieves state-of-the-art performance on few-shot NER, achieving a 5% absolute improvement in F1 score on the CoNLL2003 dataset for GPT-4. We also see large gains of upto 28.85 points (F1/Acc.) in smaller models like GPT-j-6B.</abstract>
    <identifier type="citekey">adiga-etal-2024-designing</identifier>
    <identifier type="doi">10.18653/v1/2024.findings-acl.602</identifier>
    <location>
        <url>https://aclanthology.org/2024.findings-acl.602</url>
    </location>
    <part>
        <date>2024-08</date>
        <extent unit="page">
            <start>10127</start>
            <end>10135</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Designing Informative Metrics for Few-Shot Example Selection
%A Adiga, Rishabh
%A Subramanian, Lakshmi
%A Chandrasekaran, Varun
%Y Ku, Lun-Wei
%Y Martins, Andre
%Y Srikumar, Vivek
%S Findings of the Association for Computational Linguistics: ACL 2024
%D 2024
%8 August
%I Association for Computational Linguistics
%C Bangkok, Thailand
%F adiga-etal-2024-designing
%X Pretrained language models (PLMs) have shown remarkable few-shot learning capabilities when provided with properly formatted examples. However, selecting the “best” examples remains an open challenge. We propose a complexity-based prompt selection approach for sequence tagging tasks. This approach avoids the training of a dedicated model for selection of examples, and instead uses certain metrics to align the syntactico-semantic complexity of test sentences and examples. We use both sentence- and word-level metrics to match the complexity of examples to the (test) sentence being considered. Our results demonstrate that our approach extracts greater performance from PLMs: it achieves state-of-the-art performance on few-shot NER, achieving a 5% absolute improvement in F1 score on the CoNLL2003 dataset for GPT-4. We also see large gains of upto 28.85 points (F1/Acc.) in smaller models like GPT-j-6B.
%R 10.18653/v1/2024.findings-acl.602
%U https://aclanthology.org/2024.findings-acl.602
%U https://doi.org/10.18653/v1/2024.findings-acl.602
%P 10127-10135

Markdown (Informal)

[Designing Informative Metrics for Few-Shot Example Selection](https://aclanthology.org/2024.findings-acl.602) (Adiga et al., Findings 2024)

• Designing Informative Metrics for Few-Shot Example Selection (Adiga et al., Findings 2024)

ACL

• Rishabh Adiga, Lakshmi Subramanian, and Varun Chandrasekaran. 2024. Designing Informative Metrics for Few-Shot Example Selection. In Findings of the Association for Computational Linguistics: ACL 2024, pages 10127–10135, Bangkok, Thailand. Association for Computational Linguistics.