@article{scalingupactivetestingtolargelanguagemod, title = {Scaling Up Active Testing to Large Language Models}, author = {Gabrielle Berrada and Jannik Kossen and Freddie Bickford Smith and Muhammed Razzak and Yarin Gal and Tom Rainforth}, year = {2025}, eprint = {2508.09093}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2508.09093}, }