Secrets of RLHF in Large Language Models Part I: PPO.
Resource URI: https://dblp.l3s.de/d2r/resource/publications/journals/corr/abs-2307-04964
Home
|
Example Publications
Property
Value
dcterms:
bibliographicCitation
<
http://dblp.uni-trier.de/rec/bibtex/journals/corr/abs-2307-04964
>
dc:
creator
<
https://dblp.l3s.de/d2r/resource/authors/Binghai_Wang
>
dc:
creator
<
https://dblp.l3s.de/d2r/resource/authors/Cheng_Chang
>
dc:
creator
<
https://dblp.l3s.de/d2r/resource/authors/Hang_Yan_0001
>
dc:
creator
<
https://dblp.l3s.de/d2r/resource/authors/Haoran_Huang
>
dc:
creator
<
https://dblp.l3s.de/d2r/resource/authors/Limao_Xiong
>
dc:
creator
<
https://dblp.l3s.de/d2r/resource/authors/Lu_Chen
>
dc:
creator
<
https://dblp.l3s.de/d2r/resource/authors/Minghao_Zhu
>
dc:
creator
<
https://dblp.l3s.de/d2r/resource/authors/Nuo_Xu
>
dc:
creator
<
https://dblp.l3s.de/d2r/resource/authors/Qi_Zhang_0001
>
dc:
creator
<
https://dblp.l3s.de/d2r/resource/authors/Qin_Liu
>
dc:
creator
<
https://dblp.l3s.de/d2r/resource/authors/Rongxiang_Weng
>
dc:
creator
<
https://dblp.l3s.de/d2r/resource/authors/Rui_Zheng
>
dc:
creator
<
https://dblp.l3s.de/d2r/resource/authors/Senjie_Jin
>
dc:
creator
<
https://dblp.l3s.de/d2r/resource/authors/Shihan_Dou
>
dc:
creator
<
https://dblp.l3s.de/d2r/resource/authors/Songyang_Gao
>
dc:
creator
<
https://dblp.l3s.de/d2r/resource/authors/Tao_Gui
>
dc:
creator
<
https://dblp.l3s.de/d2r/resource/authors/Tianxiang_Sun
>
dc:
creator
<
https://dblp.l3s.de/d2r/resource/authors/Wei_Shen
>
dc:
creator
<
https://dblp.l3s.de/d2r/resource/authors/Wenbin_Lai
>
dc:
creator
<
https://dblp.l3s.de/d2r/resource/authors/Wensen_Cheng
>
dc:
creator
<
https://dblp.l3s.de/d2r/resource/authors/Xipeng_Qiu
>
dc:
creator
<
https://dblp.l3s.de/d2r/resource/authors/Xuanjing_Huang_0001
>
dc:
creator
<
https://dblp.l3s.de/d2r/resource/authors/Yan_Liu
>
dc:
creator
<
https://dblp.l3s.de/d2r/resource/authors/Yuan_Hua
>
dc:
creator
<
https://dblp.l3s.de/d2r/resource/authors/Yuhao_Zhou
>
dc:
creator
<
https://dblp.l3s.de/d2r/resource/authors/Zhangyue_Yin
>
dc:
creator
<
https://dblp.l3s.de/d2r/resource/authors/Zhiheng_Xi
>
foaf:
homepage
<
http://dx.doi.org/doi.org%2F10.48550%2FarXiv.2307.04964
>
foaf:
homepage
<
https://doi.org/10.48550/arXiv.2307.04964
>
dc:
identifier
DBLP journals/corr/abs-2307-04964
(xsd:string)
dc:
identifier
DOI doi.org%2F10.48550%2FarXiv.2307.04964
(xsd:string)
dcterms:
issued
2023
(xsd:gYear)
swrc:
journal
<
https://dblp.l3s.de/d2r/resource/journals/corr
>
rdfs:
label
Secrets of RLHF in Large Language Models Part I: PPO.
(xsd:string)
foaf:
maker
<
https://dblp.l3s.de/d2r/resource/authors/Binghai_Wang
>
foaf:
maker
<
https://dblp.l3s.de/d2r/resource/authors/Cheng_Chang
>
foaf:
maker
<
https://dblp.l3s.de/d2r/resource/authors/Hang_Yan_0001
>
foaf:
maker
<
https://dblp.l3s.de/d2r/resource/authors/Haoran_Huang
>
foaf:
maker
<
https://dblp.l3s.de/d2r/resource/authors/Limao_Xiong
>
foaf:
maker
<
https://dblp.l3s.de/d2r/resource/authors/Lu_Chen
>
foaf:
maker
<
https://dblp.l3s.de/d2r/resource/authors/Minghao_Zhu
>
foaf:
maker
<
https://dblp.l3s.de/d2r/resource/authors/Nuo_Xu
>
foaf:
maker
<
https://dblp.l3s.de/d2r/resource/authors/Qi_Zhang_0001
>
foaf:
maker
<
https://dblp.l3s.de/d2r/resource/authors/Qin_Liu
>
foaf:
maker
<
https://dblp.l3s.de/d2r/resource/authors/Rongxiang_Weng
>
foaf:
maker
<
https://dblp.l3s.de/d2r/resource/authors/Rui_Zheng
>
foaf:
maker
<
https://dblp.l3s.de/d2r/resource/authors/Senjie_Jin
>
foaf:
maker
<
https://dblp.l3s.de/d2r/resource/authors/Shihan_Dou
>
foaf:
maker
<
https://dblp.l3s.de/d2r/resource/authors/Songyang_Gao
>
foaf:
maker
<
https://dblp.l3s.de/d2r/resource/authors/Tao_Gui
>
foaf:
maker
<
https://dblp.l3s.de/d2r/resource/authors/Tianxiang_Sun
>
foaf:
maker
<
https://dblp.l3s.de/d2r/resource/authors/Wei_Shen
>
foaf:
maker
<
https://dblp.l3s.de/d2r/resource/authors/Wenbin_Lai
>
foaf:
maker
<
https://dblp.l3s.de/d2r/resource/authors/Wensen_Cheng
>
foaf:
maker
<
https://dblp.l3s.de/d2r/resource/authors/Xipeng_Qiu
>
foaf:
maker
<
https://dblp.l3s.de/d2r/resource/authors/Xuanjing_Huang_0001
>
foaf:
maker
<
https://dblp.l3s.de/d2r/resource/authors/Yan_Liu
>
foaf:
maker
<
https://dblp.l3s.de/d2r/resource/authors/Yuan_Hua
>
foaf:
maker
<
https://dblp.l3s.de/d2r/resource/authors/Yuhao_Zhou
>
foaf:
maker
<
https://dblp.l3s.de/d2r/resource/authors/Zhangyue_Yin
>
foaf:
maker
<
https://dblp.l3s.de/d2r/resource/authors/Zhiheng_Xi
>
owl:
sameAs
<
http://bibsonomy.org/uri/bibtexkey/journals/corr/abs-2307-04964/dblp
>
owl:
sameAs
<
http://dblp.rkbexplorer.com/id/journals/corr/abs-2307-04964
>
rdfs:
seeAlso
<
http://dblp.uni-trier.de/db/journals/corr/corr2307.html#abs-2307-04964
>
rdfs:
seeAlso
<
https://doi.org/10.48550/arXiv.2307.04964
>
dc:
title
Secrets of RLHF in Large Language Models Part I: PPO.
(xsd:string)
dc:
type
<
http://purl.org/dc/dcmitype/Text
>
rdf:
type
swrc:Article
rdf:
type
foaf:Document
swrc:
volume
abs/2307.04964
(xsd:string)