Bioethics Bench is a shared research corpus of 200 bioethics cases and their policy options, for studying normative reasoning across AI systems, computational methods, and human judgment.
A case pairs a decision with the policies proposed for it. Each policy carries its type and how it was sourced. This is case M004, as recorded.
Three of this case's six policies are shown. Open M004 for the rest, or browse all 200 cases.
Policy type tells you what kind of perspective the policy represents.
Public, patient, participant, community, or other affected perspectives.
Professional, clinical, scientific, institutional, or governance judgments.
An identified ethical principle, theory, or framework.
See how each policy was sourced.
A source supports substantially the same policy.
The policy is a careful inference from a source.
A serious comparison policy written for the case and clearly marked as constructed.
Across 1,436 policies, 7% are directly sourced, two thirds inferred and a quarter constructed. Where the policies come from →
Bioethics Bench is being developed through careful case construction, expert consultation, and institutional collaboration. We invite researchers, practitioners, and institutions to engage with the project.
Get notified about releases, the cases, and ways to contribute.
Questions or collaboration: research@alethic.ai
If you use Bioethics Bench or the SACRE methodology in your research, please cite the introducing paper.
@article{ghose2026doingethics,
title = {Doing Ethics with AI: Practical Ethics Engineering,
Product-Led Philosophy, and Computer-Aided Ethics},
author = {Ghose, Sankalpa and Rasaee, Kasra and
Singer, Peter and Savulescu, Julian},
year = {2026}
}