<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="qi-etal-2023-pillow">
    <titleInfo>
        <title>PILLOW: Enhancing Efficient Instruction Fine-tuning via Prompt Matching</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Zhenting</namePart>
        <namePart type="family">Qi</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Xiaoyu</namePart>
        <namePart type="family">Tan</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Shaojie</namePart>
        <namePart type="family">Shi</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Chao</namePart>
        <namePart type="family">Qu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yinghui</namePart>
        <namePart type="family">Xu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yuan</namePart>
        <namePart type="family">Qi</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>Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing: Industry Track</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Mingxuan</namePart>
            <namePart type="family">Wang</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Imed</namePart>
            <namePart type="family">Zitouni</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>Instruction fine-tuning has conventionally been employed to adapt Large Language Models (LLMs) to a variety of diverse tasks. Nonetheless, this technique often necessitates substantial computational resources, making it impractical for deployment by individuals or small-scale entities. Recently, Low-Rank Adaptation (LoRA) has become a promising alternative, offering tuning capabilities with reduced resource overhead. However, attaining satisfactory performance through the fine-tuning of LoRA is a non-trivial challenge. In this paper, we propose PILLOW, which aims to improve LoRA’s performance by leveraging LLM’s in-context learning capability through prompt matching via reinforcement learning in resource-constrained environments. Specifically, PILLOW incorporates a matching network that selects prompts from a user-defined pool, concatenates the optimal prompts given the user instruction, and performs inference using the LoRA-fine-tuned LLMs. Compared with typical instruction fine-tuning methods, PILLOW exhibits commensurate performance on various evaluation metrics, utilizing only consumer-grade GPU resources and exhibiting a large increase in training efficiency.</abstract>
    <identifier type="citekey">qi-etal-2023-pillow</identifier>
    <identifier type="doi">10.18653/v1/2023.emnlp-industry.45</identifier>
    <location>
        <url>https://aclanthology.org/2023.emnlp-industry.45</url>
    </location>
    <part>
        <date>2023-12</date>
        <extent unit="page">
            <start>471</start>
            <end>482</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T PILLOW: Enhancing Efficient Instruction Fine-tuning via Prompt Matching
%A Qi, Zhenting
%A Tan, Xiaoyu
%A Shi, Shaojie
%A Qu, Chao
%A Xu, Yinghui
%A Qi, Yuan
%Y Wang, Mingxuan
%Y Zitouni, Imed
%S Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing: Industry Track
%D 2023
%8 December
%I Association for Computational Linguistics
%C Singapore
%F qi-etal-2023-pillow
%X Instruction fine-tuning has conventionally been employed to adapt Large Language Models (LLMs) to a variety of diverse tasks. Nonetheless, this technique often necessitates substantial computational resources, making it impractical for deployment by individuals or small-scale entities. Recently, Low-Rank Adaptation (LoRA) has become a promising alternative, offering tuning capabilities with reduced resource overhead. However, attaining satisfactory performance through the fine-tuning of LoRA is a non-trivial challenge. In this paper, we propose PILLOW, which aims to improve LoRA’s performance by leveraging LLM’s in-context learning capability through prompt matching via reinforcement learning in resource-constrained environments. Specifically, PILLOW incorporates a matching network that selects prompts from a user-defined pool, concatenates the optimal prompts given the user instruction, and performs inference using the LoRA-fine-tuned LLMs. Compared with typical instruction fine-tuning methods, PILLOW exhibits commensurate performance on various evaluation metrics, utilizing only consumer-grade GPU resources and exhibiting a large increase in training efficiency.
%R 10.18653/v1/2023.emnlp-industry.45
%U https://aclanthology.org/2023.emnlp-industry.45
%U https://doi.org/10.18653/v1/2023.emnlp-industry.45
%P 471-482

Markdown (Informal)

[PILLOW: Enhancing Efficient Instruction Fine-tuning via Prompt Matching](https://aclanthology.org/2023.emnlp-industry.45) (Qi et al., EMNLP 2023)

• PILLOW: Enhancing Efficient Instruction Fine-tuning via Prompt Matching (Qi et al., EMNLP 2023)

ACL

• Zhenting Qi, Xiaoyu Tan, Shaojie Shi, Chao Qu, Yinghui Xu, and Yuan Qi. 2023. PILLOW: Enhancing Efficient Instruction Fine-tuning via Prompt Matching. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing: Industry Track, pages 471–482, Singapore. Association for Computational Linguistics.