@inproceedings{zhu-etal-2024-towards,
title = "Towards an On-device Agent for Text Rewriting",
author = "Zhu, Yun and
Liu, Yinxiao and
Stahlberg, Felix and
Kumar, Shankar and
Chen, Yu-Hui and
Luo, Liangchen and
Shu, Lei and
Liu, Renjie and
Chen, Jindong and
Meng, Lei",
editor = "Duh, Kevin and
Gomez, Helena and
Bethard, Steven",
booktitle = "Findings of the Association for Computational Linguistics: NAACL 2024",
month = jun,
year = "2024",
address = "Mexico City, Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.findings-naacl.163",
pages = "2535--2552",
abstract = "Large Language Models (LLMs) have demonstrated impressive capabilities for text rewriting. However creating a smaller yet potent language model for text rewriting presents two formidable challenges: costly data collection and absence of emergent capabilities.In this paper we present solutions to address the above challenges.We propose an new instruction tuning method to develop a mo-bile text rewriting model that leverages LLM-generated data and heuristic reinforcement learning, eliminating the need for human data collection. Moreover, to bridge the performance gap from the constraint size, we pro-pose a cascading approach based on the confidence levels which are distilled from the large server model{'}s critiques. To evaluate the text rewriting tasks for mobile scenarios, we introduce MessageRewriteEval, a human-labeled benchmark that focuses on text rewriting of messages through natural language instructions. Through empirical experiments, we demonstrate that our on-device model surpasses the current state-of-the-art LLMs in text rewriting while maintaining a significantly reduced model size using public benchmark EditEval and our new benchmark. We also demonstrate that our proposed cascading approach improves model performance further.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhu-etal-2024-towards">
<titleInfo>
<title>Towards an On-device Agent for Text Rewriting</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yun</namePart>
<namePart type="family">Zhu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yinxiao</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Felix</namePart>
<namePart type="family">Stahlberg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shankar</namePart>
<namePart type="family">Kumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yu-Hui</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Liangchen</namePart>
<namePart type="family">Luo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lei</namePart>
<namePart type="family">Shu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Renjie</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jindong</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lei</namePart>
<namePart type="family">Meng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: NAACL 2024</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kevin</namePart>
<namePart type="family">Duh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Helena</namePart>
<namePart type="family">Gomez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Steven</namePart>
<namePart type="family">Bethard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Mexico City, Mexico</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Large Language Models (LLMs) have demonstrated impressive capabilities for text rewriting. However creating a smaller yet potent language model for text rewriting presents two formidable challenges: costly data collection and absence of emergent capabilities.In this paper we present solutions to address the above challenges.We propose an new instruction tuning method to develop a mo-bile text rewriting model that leverages LLM-generated data and heuristic reinforcement learning, eliminating the need for human data collection. Moreover, to bridge the performance gap from the constraint size, we pro-pose a cascading approach based on the confidence levels which are distilled from the large server model’s critiques. To evaluate the text rewriting tasks for mobile scenarios, we introduce MessageRewriteEval, a human-labeled benchmark that focuses on text rewriting of messages through natural language instructions. Through empirical experiments, we demonstrate that our on-device model surpasses the current state-of-the-art LLMs in text rewriting while maintaining a significantly reduced model size using public benchmark EditEval and our new benchmark. We also demonstrate that our proposed cascading approach improves model performance further.</abstract>
<identifier type="citekey">zhu-etal-2024-towards</identifier>
<location>
<url>https://aclanthology.org/2024.findings-naacl.163</url>
</location>
<part>
<date>2024-06</date>
<extent unit="page">
<start>2535</start>
<end>2552</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Towards an On-device Agent for Text Rewriting
%A Zhu, Yun
%A Liu, Yinxiao
%A Stahlberg, Felix
%A Kumar, Shankar
%A Chen, Yu-Hui
%A Luo, Liangchen
%A Shu, Lei
%A Liu, Renjie
%A Chen, Jindong
%A Meng, Lei
%Y Duh, Kevin
%Y Gomez, Helena
%Y Bethard, Steven
%S Findings of the Association for Computational Linguistics: NAACL 2024
%D 2024
%8 June
%I Association for Computational Linguistics
%C Mexico City, Mexico
%F zhu-etal-2024-towards
%X Large Language Models (LLMs) have demonstrated impressive capabilities for text rewriting. However creating a smaller yet potent language model for text rewriting presents two formidable challenges: costly data collection and absence of emergent capabilities.In this paper we present solutions to address the above challenges.We propose an new instruction tuning method to develop a mo-bile text rewriting model that leverages LLM-generated data and heuristic reinforcement learning, eliminating the need for human data collection. Moreover, to bridge the performance gap from the constraint size, we pro-pose a cascading approach based on the confidence levels which are distilled from the large server model’s critiques. To evaluate the text rewriting tasks for mobile scenarios, we introduce MessageRewriteEval, a human-labeled benchmark that focuses on text rewriting of messages through natural language instructions. Through empirical experiments, we demonstrate that our on-device model surpasses the current state-of-the-art LLMs in text rewriting while maintaining a significantly reduced model size using public benchmark EditEval and our new benchmark. We also demonstrate that our proposed cascading approach improves model performance further.
%U https://aclanthology.org/2024.findings-naacl.163
%P 2535-2552
Markdown (Informal)
[Towards an On-device Agent for Text Rewriting](https://aclanthology.org/2024.findings-naacl.163) (Zhu et al., Findings 2024)
ACL
- Yun Zhu, Yinxiao Liu, Felix Stahlberg, Shankar Kumar, Yu-Hui Chen, Liangchen Luo, Lei Shu, Renjie Liu, Jindong Chen, and Lei Meng. 2024. Towards an On-device Agent for Text Rewriting. In Findings of the Association for Computational Linguistics: NAACL 2024, pages 2535–2552, Mexico City, Mexico. Association for Computational Linguistics.