%0 Journal Article %1 journals/corr/abs-2311-04046 %A Cruz, Diogo %A Pona, Edoardo %A Holness-Tofts, Alex %A Schmied, Elias %A Alonso, Víctor Abia %A Griffin, Charlie %A Cirstea, Bogdan-Ionut %D 2023 %J CoRR %K dblp %T Reinforcement Learning Fine-tuning of Language Models is Biased Towards More Extractable Features. %U http://dblp.uni-trier.de/db/journals/corr/corr2311.html#abs-2311-04046 %V abs/2311.04046

@article{journals/corr/abs-2311-04046, added-at = {2024-05-07T00:00:00.000+0200}, author = {Cruz, Diogo and Pona, Edoardo and Holness-Tofts, Alex and Schmied, Elias and Alonso, Víctor Abia and Griffin, Charlie and Cirstea, Bogdan-Ionut}, biburl = {https://www.bibsonomy.org/bibtex/28806fe1e10c30d4918250f398ce8b89f/dblp}, ee = {https://doi.org/10.48550/arXiv.2311.04046}, interhash = {355872de47f1166fc3629453f2a4aa4f}, intrahash = {8806fe1e10c30d4918250f398ce8b89f}, journal = {CoRR}, keywords = {dblp}, timestamp = {2024-05-13T07:35:25.000+0200}, title = {Reinforcement Learning Fine-tuning of Language Models is Biased Towards More Extractable Features.}, url = {http://dblp.uni-trier.de/db/journals/corr/corr2311.html#abs-2311-04046}, volume = {abs/2311.04046}, year = 2023 }