Skip to content
arXiv cs.CL · Papers

MamaBench: Benchmarking LLM Robustness in Maternal and Child Health Diagnosis through Counterfactual Clinical Perturbation

arXiv:2607.14385v2 Announce Type: replace Abstract: Large language models achieve strong scores on medical benchmarks, yet these benchmarks evaluate each question in isolation, providing no measure of whether a system can distinguish clinically similar presentations requiring different interventions. We introduce MamaB