@inproceedings{zhang-etal-2024-prototypical,
title = "Prototypical Reward Network for Data-Efficient Model Alignment",
author = "Zhang, Jinghan and
Wang, Xiting and
Jin, Yiqiao and
Chen, Changyu and
Zhang, Xinhao and
Liu, Kunpeng",
editor = "Ku, Lun-Wei and
Martins, Andre and
Srikumar, Vivek",
booktitle = "Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = aug,
year = "2024",
address = "Bangkok, Thailand",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.acl-long.748",
pages = "13871--13884",
abstract = "The reward model for Reinforcement Learning from Human Feedback (RLHF) has proven effective in fine-tuning Large Language Models (LLMs). This paper explores enhancing RLHF with Prototypical Networks to improve reward models. We propose a framework utilizing Prototypical Networks to enhance reward models under limited human feedback, enabling more stable and reliable structural learning from fewer samples. This enhances the model{'}s adaptability and accuracy in interpreting human preferences. Our experiments demonstrate that this approach significantly improves the performance of reward models and LLMs in human feedback tasks, surpassing traditional methods, especially in data-limited scenarios.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhang-etal-2024-prototypical">
<titleInfo>
<title>Prototypical Reward Network for Data-Efficient Model Alignment</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jinghan</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiting</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yiqiao</namePart>
<namePart type="family">Jin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Changyu</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xinhao</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kunpeng</namePart>
<namePart type="family">Liu</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>Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</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>The reward model for Reinforcement Learning from Human Feedback (RLHF) has proven effective in fine-tuning Large Language Models (LLMs). This paper explores enhancing RLHF with Prototypical Networks to improve reward models. We propose a framework utilizing Prototypical Networks to enhance reward models under limited human feedback, enabling more stable and reliable structural learning from fewer samples. This enhances the model’s adaptability and accuracy in interpreting human preferences. Our experiments demonstrate that this approach significantly improves the performance of reward models and LLMs in human feedback tasks, surpassing traditional methods, especially in data-limited scenarios.</abstract>
<identifier type="citekey">zhang-etal-2024-prototypical</identifier>
<location>
<url>https://aclanthology.org/2024.acl-long.748</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>13871</start>
<end>13884</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Prototypical Reward Network for Data-Efficient Model Alignment
%A Zhang, Jinghan
%A Wang, Xiting
%A Jin, Yiqiao
%A Chen, Changyu
%A Zhang, Xinhao
%A Liu, Kunpeng
%Y Ku, Lun-Wei
%Y Martins, Andre
%Y Srikumar, Vivek
%S Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2024
%8 August
%I Association for Computational Linguistics
%C Bangkok, Thailand
%F zhang-etal-2024-prototypical
%X The reward model for Reinforcement Learning from Human Feedback (RLHF) has proven effective in fine-tuning Large Language Models (LLMs). This paper explores enhancing RLHF with Prototypical Networks to improve reward models. We propose a framework utilizing Prototypical Networks to enhance reward models under limited human feedback, enabling more stable and reliable structural learning from fewer samples. This enhances the model’s adaptability and accuracy in interpreting human preferences. Our experiments demonstrate that this approach significantly improves the performance of reward models and LLMs in human feedback tasks, surpassing traditional methods, especially in data-limited scenarios.
%U https://aclanthology.org/2024.acl-long.748
%P 13871-13884
Markdown (Informal)
[Prototypical Reward Network for Data-Efficient Model Alignment](https://aclanthology.org/2024.acl-long.748) (Zhang et al., ACL 2024)
ACL
- Jinghan Zhang, Xiting Wang, Yiqiao Jin, Changyu Chen, Xinhao Zhang, and Kunpeng Liu. 2024. Prototypical Reward Network for Data-Efficient Model Alignment. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 13871–13884, Bangkok, Thailand. Association for Computational Linguistics.