%0 Conference Paper %1 conf/icml/0001PMMFLBHCRP24 %A Lee, Harrison %A Phatale, Samrat %A Mansoor, Hassan %A Mesnard, Thomas %A Ferret, Johan %A Lu, Kellie %A Bishop, Colton %A Hall, Ethan %A Carbune, Victor %A Rastogi, Abhinav %A Prakash, Sushant %B ICML %D 2024 %I OpenReview.net %K dblp %T RLAIF vs. RLHF: Scaling Reinforcement Learning from Human Feedback with AI Feedback. %U http://dblp.uni-trier.de/db/conf/icml/icml2024.html#0001PMMFLBHCRP24

@inproceedings{conf/icml/0001PMMFLBHCRP24, added-at = {2024-09-02T00:00:00.000+0200}, author = {Lee, Harrison and Phatale, Samrat and Mansoor, Hassan and Mesnard, Thomas and Ferret, Johan and Lu, Kellie and Bishop, Colton and Hall, Ethan and Carbune, Victor and Rastogi, Abhinav and Prakash, Sushant}, biburl = {https://www.bibsonomy.org/bibtex/264bb172f821e9313ca697e9ffaca2928/dblp}, booktitle = {ICML}, crossref = {conf/icml/2024}, ee = {https://openreview.net/forum?id=uydQ2W41KO}, interhash = {d18e124283638a7efe252385134648cf}, intrahash = {64bb172f821e9313ca697e9ffaca2928}, keywords = {dblp}, publisher = {OpenReview.net}, timestamp = {2024-09-09T07:12:59.000+0200}, title = {RLAIF vs. RLHF: Scaling Reinforcement Learning from Human Feedback with AI Feedback.}, url = {http://dblp.uni-trier.de/db/conf/icml/icml2024.html#0001PMMFLBHCRP24}, year = 2024 }