@inproceedings{wang-etal-2024-towards-unified,
title = "Towards Unified Task Embeddings Across Multiple Models: Bridging the Gap for Prompt-Based Large Language Models and Beyond",
author = "Wang, Xinyu and
Xu, Hainiu and
Gui, Lin and
He, Yulan",
editor = "Ku, Lun-Wei and
Martins, Andre and
Srikumar, Vivek",
booktitle = "Findings of the Association for Computational Linguistics: ACL 2024",
month = aug,
year = "2024",
address = "Bangkok, Thailand",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.findings-acl.493",
doi = "10.18653/v1/2024.findings-acl.493",
pages = "8324--8340",
abstract = "Task embedding, a meta-learning technique that captures task-specific information, has gained popularity, especially in areas such as multi-task learning, model editing, and interpretability. However, it faces challenges with the emergence of prompt-guided Large Language Models (LLMs) operating in a gradient-free manner. Existing task embedding methods rely on fine-tuned, task-specific language models, which hinders the adaptability of task embeddings across diverse models, especially prompt-based LLMs. To hardness the potential of task embeddings in the era of LLMs, we propose a framework for unified task embeddings (FUTE), harmonizing task embeddings from various models, including smaller language models and LLMs with varied prompts, within a single vector space. Such uniformity enables comparison and analysis of similarities amongst different models, broadening the scope and utility of existing task embedding methods in multi-model scenarios, while maintaining their performance comparable to architecture-specific methods.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wang-etal-2024-towards-unified">
<titleInfo>
<title>Towards Unified Task Embeddings Across Multiple Models: Bridging the Gap for Prompt-Based Large Language Models and Beyond</title>
</titleInfo>
<name type="personal">
<namePart type="given">Xinyu</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hainiu</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lin</namePart>
<namePart type="family">Gui</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yulan</namePart>
<namePart type="family">He</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>Task embedding, a meta-learning technique that captures task-specific information, has gained popularity, especially in areas such as multi-task learning, model editing, and interpretability. However, it faces challenges with the emergence of prompt-guided Large Language Models (LLMs) operating in a gradient-free manner. Existing task embedding methods rely on fine-tuned, task-specific language models, which hinders the adaptability of task embeddings across diverse models, especially prompt-based LLMs. To hardness the potential of task embeddings in the era of LLMs, we propose a framework for unified task embeddings (FUTE), harmonizing task embeddings from various models, including smaller language models and LLMs with varied prompts, within a single vector space. Such uniformity enables comparison and analysis of similarities amongst different models, broadening the scope and utility of existing task embedding methods in multi-model scenarios, while maintaining their performance comparable to architecture-specific methods.</abstract>
<identifier type="citekey">wang-etal-2024-towards-unified</identifier>
<identifier type="doi">10.18653/v1/2024.findings-acl.493</identifier>
<location>
<url>https://aclanthology.org/2024.findings-acl.493</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>8324</start>
<end>8340</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Towards Unified Task Embeddings Across Multiple Models: Bridging the Gap for Prompt-Based Large Language Models and Beyond
%A Wang, Xinyu
%A Xu, Hainiu
%A Gui, Lin
%A He, Yulan
%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 wang-etal-2024-towards-unified
%X Task embedding, a meta-learning technique that captures task-specific information, has gained popularity, especially in areas such as multi-task learning, model editing, and interpretability. However, it faces challenges with the emergence of prompt-guided Large Language Models (LLMs) operating in a gradient-free manner. Existing task embedding methods rely on fine-tuned, task-specific language models, which hinders the adaptability of task embeddings across diverse models, especially prompt-based LLMs. To hardness the potential of task embeddings in the era of LLMs, we propose a framework for unified task embeddings (FUTE), harmonizing task embeddings from various models, including smaller language models and LLMs with varied prompts, within a single vector space. Such uniformity enables comparison and analysis of similarities amongst different models, broadening the scope and utility of existing task embedding methods in multi-model scenarios, while maintaining their performance comparable to architecture-specific methods.
%R 10.18653/v1/2024.findings-acl.493
%U https://aclanthology.org/2024.findings-acl.493
%U https://doi.org/10.18653/v1/2024.findings-acl.493
%P 8324-8340
Markdown (Informal)
[Towards Unified Task Embeddings Across Multiple Models: Bridging the Gap for Prompt-Based Large Language Models and Beyond](https://aclanthology.org/2024.findings-acl.493) (Wang et al., Findings 2024)
ACL