%0 Journal Article %1 journals/corr/abs-2402-13228 %A Pal, Arka %A Karkhanis, Deep %A Dooley, Samuel %A Roberts, Manley %A Naidu, Siddartha %A White, Colin %D 2024 %J CoRR %K dblp %T Smaug: Fixing Failure Modes of Preference Optimisation with DPO-Positive. %U http://dblp.uni-trier.de/db/journals/corr/corr2402.html#abs-2402-13228 %V abs/2402.13228

@article{journals/corr/abs-2402-13228, added-at = {2024-03-21T00:00:00.000+0100}, author = {Pal, Arka and Karkhanis, Deep and Dooley, Samuel and Roberts, Manley and Naidu, Siddartha and White, Colin}, biburl = {https://www.bibsonomy.org/bibtex/28010c93fbc968a574b85687ac95a14d2/dblp}, ee = {https://doi.org/10.48550/arXiv.2402.13228}, interhash = {e04658f64cbc636e39a43b48a9b7bdce}, intrahash = {8010c93fbc968a574b85687ac95a14d2}, journal = {CoRR}, keywords = {dblp}, timestamp = {2024-04-09T00:07:02.000+0200}, title = {Smaug: Fixing Failure Modes of Preference Optimisation with DPO-Positive.}, url = {http://dblp.uni-trier.de/db/journals/corr/corr2402.html#abs-2402-13228}, volume = {abs/2402.13228}, year = 2024 }