<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wang-lim-2024-whole">
    <titleInfo>
        <title>The Whole is Better than the Sum: Using Aggregated Demonstrations in In-Context Learning for Sequential Recommendation</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Lei</namePart>
        <namePart type="family">Wang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Ee-Peng</namePart>
        <namePart type="family">Lim</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>Findings of the Association for Computational Linguistics: NAACL 2024</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Kevin</namePart>
            <namePart type="family">Duh</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Helena</namePart>
            <namePart type="family">Gomez</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Steven</namePart>
            <namePart type="family">Bethard</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) have shown excellent performance on various NLP tasks. To use LLMs as strong sequential recommenders, we explore the in-context learning approach to sequential recommendation. We investigate the effects of instruction format, task consistency, demonstration selection, and number of demonstrations. As increasing the number of demonstrations in ICL does not improve accuracy despite using a long prompt, we propose a novel method called LLMSRec-Syn that incorporates multiple demonstration users into one aggregated demonstration. Our experiments on three recommendation datasets show that LLMSRec-Syn outperforms state-of-the-art LLM-based sequential recommendation methods. In some cases, LLMSRec-Syn can perform on par with or even better than supervised learning methods. Our code is publicly available at https://github.com/demoleiwang/LLMSRec_Syn.</abstract>
    <identifier type="citekey">wang-lim-2024-whole</identifier>
    <identifier type="doi">10.18653/v1/2024.findings-naacl.56</identifier>
    <location>
        <url>https://aclanthology.org/2024.findings-naacl.56</url>
    </location>
    <part>
        <date>2024-06</date>
        <extent unit="page">
            <start>876</start>
            <end>895</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T The Whole is Better than the Sum: Using Aggregated Demonstrations in In-Context Learning for Sequential Recommendation
%A Wang, Lei
%A Lim, Ee-Peng
%Y Duh, Kevin
%Y Gomez, Helena
%Y Bethard, Steven
%S Findings of the Association for Computational Linguistics: NAACL 2024
%D 2024
%8 June
%I Association for Computational Linguistics
%C Mexico City, Mexico
%F wang-lim-2024-whole
%X Large language models (LLMs) have shown excellent performance on various NLP tasks. To use LLMs as strong sequential recommenders, we explore the in-context learning approach to sequential recommendation. We investigate the effects of instruction format, task consistency, demonstration selection, and number of demonstrations. As increasing the number of demonstrations in ICL does not improve accuracy despite using a long prompt, we propose a novel method called LLMSRec-Syn that incorporates multiple demonstration users into one aggregated demonstration. Our experiments on three recommendation datasets show that LLMSRec-Syn outperforms state-of-the-art LLM-based sequential recommendation methods. In some cases, LLMSRec-Syn can perform on par with or even better than supervised learning methods. Our code is publicly available at https://github.com/demoleiwang/LLMSRec_Syn.
%R 10.18653/v1/2024.findings-naacl.56
%U https://aclanthology.org/2024.findings-naacl.56
%U https://doi.org/10.18653/v1/2024.findings-naacl.56
%P 876-895

Markdown (Informal)

[The Whole is Better than the Sum: Using Aggregated Demonstrations in In-Context Learning for Sequential Recommendation](https://aclanthology.org/2024.findings-naacl.56) (Wang & Lim, Findings 2024)

• The Whole is Better than the Sum: Using Aggregated Demonstrations in In-Context Learning for Sequential Recommendation (Wang & Lim, Findings 2024)

ACL

• Lei Wang and Ee-Peng Lim. 2024. The Whole is Better than the Sum: Using Aggregated Demonstrations in In-Context Learning for Sequential Recommendation. In Findings of the Association for Computational Linguistics: NAACL 2024, pages 876–895, Mexico City, Mexico. Association for Computational Linguistics.