@inproceedings{viswanathan-etal-2023-prompt2model,
title = "{P}rompt2{M}odel: Generating Deployable Models from Natural Language Instructions",
author = "Viswanathan, Vijay and
Zhao, Chenyang and
Bertsch, Amanda and
Wu, Tongshuang and
Neubig, Graham",
editor = "Feng, Yansong and
Lefever, Els",
booktitle = "Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing: System Demonstrations",
month = dec,
year = "2023",
address = "Singapore",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.emnlp-demo.38",
doi = "10.18653/v1/2023.emnlp-demo.38",
pages = "413--421",
abstract = "Large language models (LLMs) enable system builders today to create competent NLP systems through prompting, where they only need to describe the task in natural language and provide a few examples. However, in other ways, LLMs are a step backward from traditional special-purpose NLP models; they require extensive computational resources for deployment and can be gated behind APIs. In this paper, we propose Prompt2Model, a general-purpose method that takes a natural language task description like the prompts provided to LLMs, and uses it to train a special-purpose model that is conducive to deployment. This is done through a multi-step process of retrieval of existing datasets and pretrained models, dataset generation using LLMs, and supervised fine-tuning on these retrieved and generated datasets. Over three tasks, we demonstrate that given the same few-shot prompt as input, Prompt2Model trains models that outperform the results of a strong LLM, gpt-3.5-turbo, by an average of 20{\%} while being up to 700 times smaller. We also show that this data can be used to obtain reliable performance estimates of model performance, enabling model developers to assess model reliability before deployment. Prompt2Model is available open-source at https://github.com/neulab/prompt2model. Our demo video is posted at \url{youtu.be/LYYQ_EhGd-Q}.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="viswanathan-etal-2023-prompt2model">
<titleInfo>
<title>Prompt2Model: Generating Deployable Models from Natural Language Instructions</title>
</titleInfo>
<name type="personal">
<namePart type="given">Vijay</namePart>
<namePart type="family">Viswanathan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chenyang</namePart>
<namePart type="family">Zhao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Amanda</namePart>
<namePart type="family">Bertsch</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tongshuang</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Graham</namePart>
<namePart type="family">Neubig</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: System Demonstrations</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yansong</namePart>
<namePart type="family">Feng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Els</namePart>
<namePart type="family">Lefever</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>Large language models (LLMs) enable system builders today to create competent NLP systems through prompting, where they only need to describe the task in natural language and provide a few examples. However, in other ways, LLMs are a step backward from traditional special-purpose NLP models; they require extensive computational resources for deployment and can be gated behind APIs. In this paper, we propose Prompt2Model, a general-purpose method that takes a natural language task description like the prompts provided to LLMs, and uses it to train a special-purpose model that is conducive to deployment. This is done through a multi-step process of retrieval of existing datasets and pretrained models, dataset generation using LLMs, and supervised fine-tuning on these retrieved and generated datasets. Over three tasks, we demonstrate that given the same few-shot prompt as input, Prompt2Model trains models that outperform the results of a strong LLM, gpt-3.5-turbo, by an average of 20% while being up to 700 times smaller. We also show that this data can be used to obtain reliable performance estimates of model performance, enabling model developers to assess model reliability before deployment. Prompt2Model is available open-source at https://github.com/neulab/prompt2model. Our demo video is posted at youtu.be/LYYQ_EhGd-Q.</abstract>
<identifier type="citekey">viswanathan-etal-2023-prompt2model</identifier>
<identifier type="doi">10.18653/v1/2023.emnlp-demo.38</identifier>
<location>
<url>https://aclanthology.org/2023.emnlp-demo.38</url>
</location>
<part>
<date>2023-12</date>
<extent unit="page">
<start>413</start>
<end>421</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Prompt2Model: Generating Deployable Models from Natural Language Instructions
%A Viswanathan, Vijay
%A Zhao, Chenyang
%A Bertsch, Amanda
%A Wu, Tongshuang
%A Neubig, Graham
%Y Feng, Yansong
%Y Lefever, Els
%S Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing: System Demonstrations
%D 2023
%8 December
%I Association for Computational Linguistics
%C Singapore
%F viswanathan-etal-2023-prompt2model
%X Large language models (LLMs) enable system builders today to create competent NLP systems through prompting, where they only need to describe the task in natural language and provide a few examples. However, in other ways, LLMs are a step backward from traditional special-purpose NLP models; they require extensive computational resources for deployment and can be gated behind APIs. In this paper, we propose Prompt2Model, a general-purpose method that takes a natural language task description like the prompts provided to LLMs, and uses it to train a special-purpose model that is conducive to deployment. This is done through a multi-step process of retrieval of existing datasets and pretrained models, dataset generation using LLMs, and supervised fine-tuning on these retrieved and generated datasets. Over three tasks, we demonstrate that given the same few-shot prompt as input, Prompt2Model trains models that outperform the results of a strong LLM, gpt-3.5-turbo, by an average of 20% while being up to 700 times smaller. We also show that this data can be used to obtain reliable performance estimates of model performance, enabling model developers to assess model reliability before deployment. Prompt2Model is available open-source at https://github.com/neulab/prompt2model. Our demo video is posted at youtu.be/LYYQ_EhGd-Q.
%R 10.18653/v1/2023.emnlp-demo.38
%U https://aclanthology.org/2023.emnlp-demo.38
%U https://doi.org/10.18653/v1/2023.emnlp-demo.38
%P 413-421
Markdown (Informal)
[Prompt2Model: Generating Deployable Models from Natural Language Instructions](https://aclanthology.org/2023.emnlp-demo.38) (Viswanathan et al., EMNLP 2023)
ACL