Benchmarks › Ethics

Ethics

Benchmark measures model capacity for reflecting human notions of justice, well-being, duties, virtues, and commonsense morality

Full title

Aligning AI With Shared Human Values

Tag

ethics (use this to limit an assistant's search to this benchmark)

Reference

arxiv.org/abs/2008.02275

BenchRisk

Scored 2025-04-01 · 31 mitigations adopted, 155 absent · score page · source entry

Documents available to assistants

Summary from the reference

We show how to assess a language model's knowledge of basic concepts of morality. We introduce the ETHICS dataset, a new benchmark that spans concepts in justice, well-being, duties, virtues, and commonsense morality. Models predict widespread moral judgments about diverse text scenarios. This requires connecting physical and social world knowledge to value judgements, a capability that may enable us to steer chatbot outputs or eventually regularize open-ended reinforcement learning agents. With the ETHICS dataset, we find that current language models have a promising but incomplete ability to predict basic human ethical judgements. Our work shows that progress can be made on machine ethics today, and it provides a steppingstone toward AI that is aligned with human values.

Ask an assistant about it

Once your assistant is connected, try a question such as “Using the benchmark sources, how is Ethics scored?”

Developers can restrict a search to this benchmark with the filter {"benchmark": "ethics"} on the MCP endpoint https://ns-f1fc49e3-9bca-4aa2-b5a1-ef5dbc18588f.search.ai.cloudflare.com/mcp.