Aligning AI With Shared Human Values

Dan Hendrycks · Collin Burns · Steven Basart · Andrew Critch · Jerry Zheng Li · Dawn Xiaodong Song +1 more

166 citations0/0 files storedarXiv (Cornell University)

No readable copy stored yet — this record is metadata only.

No open-access location is known for this record yet.

Literature note Cite in a project Citation map

Ethics and Social Impacts of AI Ethics in Business and Education Psychology of Moral and Emotional Judgment

Abstract

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.

Paper brief

Loading…

Cite this work

Citation unavailable for this work.

BibTeX RIS CSL-JSON

No public copy is stored for this record, so only the metadata is cited.

Citations in this library

Citation map →

Stored only when both papers are in the corpus — 166 citations exist upstream.

References

2019Theory of games and economic behavior 2019HISTORIAE, History of Socio-Cultural Transformation as Linguistic Data Science. A Humanities Use Case 1739A Treatise of Human Nature 2017An Introduction to the Principles of Morals and Legislation 2020Groundwork of The Metaphysic of Morals 2016Equality of Opportunity in Supervised Learning 2003CAPABILITIES AS FUNDAMENTAL ENTITLEMENTS: SEN AND SOCIAL JUSTICE 2015Superintelligence: paths, dangers, strategies

Cited by

2021When does pretraining help?2021Unsolved Problems in ML Safety 2021Aligning artificial intelligence with human values: reflections from a phenomenological perspective 2021Delphi: Towards Machine Ethics and Norms 2023Probing Pre-Trained Language Models for Cross-Cultural Differences in Values 2022The Dangers of Underclaiming: Reasons for Caution When Reporting How NLP Systems Fail

Explore the map →

Papers that cite the same references — the relational fallback while embeddings are still backfilling.

Imported from OpenAlex (CC0) — nothing here is generated.