@inproceedings{yang-etal-2024-preference,
title = "Not All Preference Pairs Are Created Equal: A Recipe for Annotation-Efficient Iterative Preference Learning",
author = "Yang, Sen and
Cui, Leyang and
Cai, Deng and
Huang, Xinting and
Shi, Shuming and
Lam, Wai",
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.382",
pages = "6549--6561",
abstract = "Iterative preference learning, though yielding superior performances, requires online annotated preference labels. In this work, we study strategies to save annotation budgets while achieving competitive or even better performances for iterative preference learning. Built on intuitions from active learning, we empirically show that annotating those response pairs with $small$ margins is generally better than $large$ or $random$. Besides, experiments under the multi-iteration scenario suggest allocating more annotation budgets in the earlier iterations rather than later ones.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yang-etal-2024-preference">
<titleInfo>
<title>Not All Preference Pairs Are Created Equal: A Recipe for Annotation-Efficient Iterative Preference Learning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sen</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Leyang</namePart>
<namePart type="family">Cui</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Deng</namePart>
<namePart type="family">Cai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xinting</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shuming</namePart>
<namePart type="family">Shi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wai</namePart>
<namePart type="family">Lam</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>Iterative preference learning, though yielding superior performances, requires online annotated preference labels. In this work, we study strategies to save annotation budgets while achieving competitive or even better performances for iterative preference learning. Built on intuitions from active learning, we empirically show that annotating those response pairs with small margins is generally better than large or random. Besides, experiments under the multi-iteration scenario suggest allocating more annotation budgets in the earlier iterations rather than later ones.</abstract>
<identifier type="citekey">yang-etal-2024-preference</identifier>
<location>
<url>https://aclanthology.org/2024.findings-emnlp.382</url>
</location>
<part>
<date>2024-11</date>
<extent unit="page">
<start>6549</start>
<end>6561</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Not All Preference Pairs Are Created Equal: A Recipe for Annotation-Efficient Iterative Preference Learning
%A Yang, Sen
%A Cui, Leyang
%A Cai, Deng
%A Huang, Xinting
%A Shi, Shuming
%A Lam, Wai
%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 yang-etal-2024-preference
%X Iterative preference learning, though yielding superior performances, requires online annotated preference labels. In this work, we study strategies to save annotation budgets while achieving competitive or even better performances for iterative preference learning. Built on intuitions from active learning, we empirically show that annotating those response pairs with small margins is generally better than large or random. Besides, experiments under the multi-iteration scenario suggest allocating more annotation budgets in the earlier iterations rather than later ones.
%U https://aclanthology.org/2024.findings-emnlp.382
%P 6549-6561
Markdown (Informal)
[Not All Preference Pairs Are Created Equal: A Recipe for Annotation-Efficient Iterative Preference Learning](https://aclanthology.org/2024.findings-emnlp.382) (Yang et al., Findings 2024)
ACL