@inproceedings{xin-etal-2024-beyond,
title = "Beyond Full Fine-tuning: Harnessing the Power of {L}o{RA} for Multi-Task Instruction Tuning",
author = "Xin, Chunlei and
Lu, Yaojie and
Lin, Hongyu and
Zhou, Shuheng and
Zhu, Huijia and
Wang, Weiqiang and
Liu, Zhongyi and
Han, Xianpei and
Sun, Le",
editor = "Calzolari, Nicoletta and
Kan, Min-Yen and
Hoste, Veronique and
Lenci, Alessandro and
Sakti, Sakriani and
Xue, Nianwen",
booktitle = "Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.lrec-main.206",
pages = "2307--2317",
abstract = "Low-Rank Adaptation (LoRA) is a widespread parameter-efficient fine-tuning algorithm for large-scale language models. It has been commonly accepted that LoRA mostly achieves promising results in single-task, low-resource settings, and struggles to handle multi-task instruction tuning scenarios. In this paper, we conduct a systematic study of LoRA on diverse tasks and rich resources with different learning capacities, examining its performance on seen tasks during training and its cross-task generalization on unseen tasks. Our findings challenge the prevalent assumption that the limited learning capacity will inevitably result in performance decline. In fact, our study reveals that when configured with an appropriate rank, LoRA can achieve remarkable performance in high-resource and multi-task scenarios, even comparable to that achieved through full fine-tuning. It turns out that the constrained learning capacity encourages LoRA to prioritize conforming to instruction requirements rather than memorizing specialized features of particular tasks or instances. This study reveals the underlying connection between learning capacity and generalization capabilities for robust parameter-efficient fine-tuning, highlighting a promising direction for the broader application of LoRA across various tasks and settings.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="xin-etal-2024-beyond">
<titleInfo>
<title>Beyond Full Fine-tuning: Harnessing the Power of LoRA for Multi-Task Instruction Tuning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Chunlei</namePart>
<namePart type="family">Xin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yaojie</namePart>
<namePart type="family">Lu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hongyu</namePart>
<namePart type="family">Lin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shuheng</namePart>
<namePart type="family">Zhou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Huijia</namePart>
<namePart type="family">Zhu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Weiqiang</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhongyi</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xianpei</namePart>
<namePart type="family">Han</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Le</namePart>
<namePart type="family">Sun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Min-Yen</namePart>
<namePart type="family">Kan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Veronique</namePart>
<namePart type="family">Hoste</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Lenci</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA and ICCL</publisher>
<place>
<placeTerm type="text">Torino, Italia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Low-Rank Adaptation (LoRA) is a widespread parameter-efficient fine-tuning algorithm for large-scale language models. It has been commonly accepted that LoRA mostly achieves promising results in single-task, low-resource settings, and struggles to handle multi-task instruction tuning scenarios. In this paper, we conduct a systematic study of LoRA on diverse tasks and rich resources with different learning capacities, examining its performance on seen tasks during training and its cross-task generalization on unseen tasks. Our findings challenge the prevalent assumption that the limited learning capacity will inevitably result in performance decline. In fact, our study reveals that when configured with an appropriate rank, LoRA can achieve remarkable performance in high-resource and multi-task scenarios, even comparable to that achieved through full fine-tuning. It turns out that the constrained learning capacity encourages LoRA to prioritize conforming to instruction requirements rather than memorizing specialized features of particular tasks or instances. This study reveals the underlying connection between learning capacity and generalization capabilities for robust parameter-efficient fine-tuning, highlighting a promising direction for the broader application of LoRA across various tasks and settings.</abstract>
<identifier type="citekey">xin-etal-2024-beyond</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.206</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>2307</start>
<end>2317</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Beyond Full Fine-tuning: Harnessing the Power of LoRA for Multi-Task Instruction Tuning
%A Xin, Chunlei
%A Lu, Yaojie
%A Lin, Hongyu
%A Zhou, Shuheng
%A Zhu, Huijia
%A Wang, Weiqiang
%A Liu, Zhongyi
%A Han, Xianpei
%A Sun, Le
%Y Calzolari, Nicoletta
%Y Kan, Min-Yen
%Y Hoste, Veronique
%Y Lenci, Alessandro
%Y Sakti, Sakriani
%Y Xue, Nianwen
%S Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F xin-etal-2024-beyond
%X Low-Rank Adaptation (LoRA) is a widespread parameter-efficient fine-tuning algorithm for large-scale language models. It has been commonly accepted that LoRA mostly achieves promising results in single-task, low-resource settings, and struggles to handle multi-task instruction tuning scenarios. In this paper, we conduct a systematic study of LoRA on diverse tasks and rich resources with different learning capacities, examining its performance on seen tasks during training and its cross-task generalization on unseen tasks. Our findings challenge the prevalent assumption that the limited learning capacity will inevitably result in performance decline. In fact, our study reveals that when configured with an appropriate rank, LoRA can achieve remarkable performance in high-resource and multi-task scenarios, even comparable to that achieved through full fine-tuning. It turns out that the constrained learning capacity encourages LoRA to prioritize conforming to instruction requirements rather than memorizing specialized features of particular tasks or instances. This study reveals the underlying connection between learning capacity and generalization capabilities for robust parameter-efficient fine-tuning, highlighting a promising direction for the broader application of LoRA across various tasks and settings.
%U https://aclanthology.org/2024.lrec-main.206
%P 2307-2317
Markdown (Informal)
[Beyond Full Fine-tuning: Harnessing the Power of LoRA for Multi-Task Instruction Tuning](https://aclanthology.org/2024.lrec-main.206) (Xin et al., LREC-COLING 2024)
ACL
- Chunlei Xin, Yaojie Lu, Hongyu Lin, Shuheng Zhou, Huijia Zhu, Weiqiang Wang, Zhongyi Liu, Xianpei Han, and Le Sun. 2024. Beyond Full Fine-tuning: Harnessing the Power of LoRA for Multi-Task Instruction Tuning. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 2307–2317, Torino, Italia. ELRA and ICCL.