@article{diagnosingourdatasetshowdoesmylanguage, title = {Diagnosing our datasets: How does my language model learn clinical information?}, author = {Furong Jia and David Sontag and Monica Agrawal}, year = {2025}, eprint = {2505.15024}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2505.15024v1}, }