@inproceedings{lu-etal-2024-hit,
title = "Hit the Nail on the Head: Parameter-Efficient Multi-task Tuning via Human Language Intervention",
author = "Lu, Wenxuan and
Jiang, Songhao and
Yijing, Wang and
Zang, Tianning",
editor = "Al-Onaizan, Yaser and
Bansal, Mohit and
Chen, Yun-Nung",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2024",
month = nov,
year = "2024",
address = "Miami, Florida, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.findings-emnlp.518",
doi = "10.18653/v1/2024.findings-emnlp.518",
pages = "8873--8885",
abstract = "Parameter-Efficient Fine-Tuning (PEFT) on small Pre-trained Language Models (PLMs) has emerged as a promising approach to enhance their multi-tasking capabilities. Prevalent methods simultaneously train additional modules (i.e., one task-shared module and multiple task-specific modules) for adapting PLMs to downstream tasks. However, their adaptability to new tasks is constrained, as the task-specific modules independently adapt to each task, overlooking the potential for knowledge transfer across tasks. In this paper, we propose a novel multi-task learning framework, Inspirational Pointer (IP), that enables the transfer of prior knowledge across tasks through human language intervention. Specifically, we attach task descriptions to the input samples, which are then mapped to corresponding task embeddings. Based on those embeddings, we adapt PLMs for downstream tasks. Similar tasks share akin descriptions, allowing new task samples close to similar trained tasks in the task embedding space, hitting the memory about trained tasks of the model. Our experiments on the T5 model demonstrate performance improvements of our method in multi-task learning and few-shot transfer learning. Further, we implemented the IP in decoder-only models including GPT2 and large language models (LLMs), and the results show that IP enhances the capabilities of decoder-only models.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lu-etal-2024-hit">
<titleInfo>
<title>Hit the Nail on the Head: Parameter-Efficient Multi-task Tuning via Human Language Intervention</title>
</titleInfo>
<name type="personal">
<namePart type="given">Wenxuan</namePart>
<namePart type="family">Lu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Songhao</namePart>
<namePart type="family">Jiang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wang</namePart>
<namePart type="family">Yijing</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tianning</namePart>
<namePart type="family">Zang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2024</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yaser</namePart>
<namePart type="family">Al-Onaizan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohit</namePart>
<namePart type="family">Bansal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yun-Nung</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Miami, Florida, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Parameter-Efficient Fine-Tuning (PEFT) on small Pre-trained Language Models (PLMs) has emerged as a promising approach to enhance their multi-tasking capabilities. Prevalent methods simultaneously train additional modules (i.e., one task-shared module and multiple task-specific modules) for adapting PLMs to downstream tasks. However, their adaptability to new tasks is constrained, as the task-specific modules independently adapt to each task, overlooking the potential for knowledge transfer across tasks. In this paper, we propose a novel multi-task learning framework, Inspirational Pointer (IP), that enables the transfer of prior knowledge across tasks through human language intervention. Specifically, we attach task descriptions to the input samples, which are then mapped to corresponding task embeddings. Based on those embeddings, we adapt PLMs for downstream tasks. Similar tasks share akin descriptions, allowing new task samples close to similar trained tasks in the task embedding space, hitting the memory about trained tasks of the model. Our experiments on the T5 model demonstrate performance improvements of our method in multi-task learning and few-shot transfer learning. Further, we implemented the IP in decoder-only models including GPT2 and large language models (LLMs), and the results show that IP enhances the capabilities of decoder-only models.</abstract>
<identifier type="citekey">lu-etal-2024-hit</identifier>
<identifier type="doi">10.18653/v1/2024.findings-emnlp.518</identifier>
<location>
<url>https://aclanthology.org/2024.findings-emnlp.518</url>
</location>
<part>
<date>2024-11</date>
<extent unit="page">
<start>8873</start>
<end>8885</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Hit the Nail on the Head: Parameter-Efficient Multi-task Tuning via Human Language Intervention
%A Lu, Wenxuan
%A Jiang, Songhao
%A Yijing, Wang
%A Zang, Tianning
%Y Al-Onaizan, Yaser
%Y Bansal, Mohit
%Y Chen, Yun-Nung
%S Findings of the Association for Computational Linguistics: EMNLP 2024
%D 2024
%8 November
%I Association for Computational Linguistics
%C Miami, Florida, USA
%F lu-etal-2024-hit
%X Parameter-Efficient Fine-Tuning (PEFT) on small Pre-trained Language Models (PLMs) has emerged as a promising approach to enhance their multi-tasking capabilities. Prevalent methods simultaneously train additional modules (i.e., one task-shared module and multiple task-specific modules) for adapting PLMs to downstream tasks. However, their adaptability to new tasks is constrained, as the task-specific modules independently adapt to each task, overlooking the potential for knowledge transfer across tasks. In this paper, we propose a novel multi-task learning framework, Inspirational Pointer (IP), that enables the transfer of prior knowledge across tasks through human language intervention. Specifically, we attach task descriptions to the input samples, which are then mapped to corresponding task embeddings. Based on those embeddings, we adapt PLMs for downstream tasks. Similar tasks share akin descriptions, allowing new task samples close to similar trained tasks in the task embedding space, hitting the memory about trained tasks of the model. Our experiments on the T5 model demonstrate performance improvements of our method in multi-task learning and few-shot transfer learning. Further, we implemented the IP in decoder-only models including GPT2 and large language models (LLMs), and the results show that IP enhances the capabilities of decoder-only models.
%R 10.18653/v1/2024.findings-emnlp.518
%U https://aclanthology.org/2024.findings-emnlp.518
%U https://doi.org/10.18653/v1/2024.findings-emnlp.518
%P 8873-8885
Markdown (Informal)
[Hit the Nail on the Head: Parameter-Efficient Multi-task Tuning via Human Language Intervention](https://aclanthology.org/2024.findings-emnlp.518) (Lu et al., Findings 2024)
ACL