JASA
On the Algorithmic Bias of Aligning Large Language Models with RLHF: Preference Collapse and Matching Regularization
Authors
Jiancong Xiao
Ziniu Li
Xingyu Xie
Emily Getzen
Cong Fang
Qi Long
Weijie J. Su
Research Topics
High-Dimensional Statistics
Computational Statistics
Paper Information
-
Journal:
Journal of the American Statistical Association -
DOI:
10.1080/01621459.2025.2555067 -
Added to Tracker:
Sep 24, 2025
Author Details
Jiancong Xiao
AuthorZiniu Li
AuthorXingyu Xie
AuthorEmily Getzen
AuthorCong Fang
AuthorQi Long
AuthorWeijie J. Su
AuthorResearch Topics & Keywords
High-Dimensional Statistics
Research AreaComputational Statistics
Research AreaCitation Information
APA Format
Jiancong Xiao
,
Ziniu Li
,
Xingyu Xie
,
Emily Getzen
,
Cong Fang
,
Qi Long
&
Weijie J. Su
.
On the Algorithmic Bias of Aligning Large Language Models with RLHF: Preference Collapse and Matching Regularization.
Journal of the American Statistical Association
, 10.1080/01621459.2025.2555067.
BibTeX Format
@article{paper541,
title = { On the Algorithmic Bias of Aligning Large Language Models with RLHF: Preference Collapse and Matching Regularization },
author = {
Jiancong Xiao
and Ziniu Li
and Xingyu Xie
and Emily Getzen
and Cong Fang
and Qi Long
and Weijie J. Su
},
journal = { Journal of the American Statistical Association },
doi = { 10.1080/01621459.2025.2555067 },
url = { https://www.tandfonline.com/doi/full/10.1080/01621459.2025.2555067 }
}