Procedural Dilemma Generation for Evaluating Moral Reasoning in Humans and Language Models

As AI systems like language models are increasingly integrated into decision-making processes affecting people's lives, it's critical to ensure that these systems have sound moral reasoning. To test whether they do, we need to develop systematic evaluations. We provide a framework that uses a language model to translate causal graphs that capture key aspects of moral dilemmas into prompt templates. With this framework, we procedurally generated a large and diverse set of moral dilemmas -- the OffTheRails benchmark -- consisting of 50 scenarios and 400 unique test items. We collected moral permissibility and intention judgments from human participants for a subset of our items and compared these judgments to those from two language models (GPT-4 and Claude-2) across eight conditions. We find that moral dilemmas in which the harm is a necessary means (as compared to a side effect) resulted in lower permissibility and higher intention ratings for both participants and language models. The same pattern was observed for evitable versus inevitable harmful outcomes. However, there was no clear effect of whether the harm resulted from an agent's action versus from having omitted to act. We discuss limitations of our prompt generation pipeline and opportunities for improving scenarios to increase the strength of experimental effects.

Federated Learning on Patient Data for Privacy-Protecting Polycystic Ovary Syndrome Treatment

The field of women's endocrinology has trailed behind data-driven medical solutions, largely due to concerns over the privacy of patient data. Valuable datapoints about hormone levels or menstrual cycling could expose patients who suffer from comorbidities or terminate a pregnancy, violating their privacy. We explore the application of Federated Learning (FL) to predict the optimal drug for patients with polycystic ovary syndrome (PCOS). PCOS is a serious hormonal disorder impacting millions of women worldwide, yet it's poorly understood and its research is stunted by a lack of patient data. We demonstrate that a variety of FL approaches succeed on a synthetic PCOS patient dataset. Our proposed FL models are a tool to access massive quantities of diverse data and identify the most effective treatment option while providing PCOS patients with privacy guarantees.