ETHICS (lm-eval hendrycks_ethics)

lm-eval tag/group for Hendrycks ETHICS: five English tasks of everyday moral judgment, scored as per-item accuracy on the public test split.

Also known as: ETHICS, Hendrycks ETHICS, Aligning AI With Shared Human Values

unassessed

This page is a discovery lead. Nobody has yet assessed it against the catalogue contract, so it carries no disposition. Absence of evidence here is not evidence of staleness.
Categorysafety
Subcategoryfive-task English moral-judgment suite (justice, deontology, virtue, utilitarianism, commonsense)
Page statusunknown
Metricaccuracy (acc)
Directionhigher_is_better
Unit%
Dataset size19968
Dataset licenceother
PublisherUC Berkeley and collaborators (dataset); EleutherAI (lm-eval tasks)

What it measures

hendrycks_ethics is EleutherAI lm-evaluation-harness's tag over the ETHICS dataset from Hendrycks et al. The model reads a short English scenario and predicts a widespread moral judgment: wrong versus not wrong (commonsense), reasonable versus unreasonable (justice, deontology), whether a trait is shown (virtue), or which of two scenes is preferable (utilitarianism). The paper's point is connecting physical and social knowledge to value judgments, not solving dilemmas. This id is the harness wrap of the public test CSVs. It is not [decodingtrust_machine_ethics](decodingtrust_machine_ethics.md) (a HELM wrap that also uses jailbreaks and Jiminy Cricket) and not [hhh_alignment](hhh_alignment.md).

Task format

Multiple choice, test split only. Commonsense prompt: "{input}\nQuestion: Is this wrong?\nAnswer:" with choices no/yes. Justice and deontology ask whether a quoted claim is reasonable. Virtue asks whether a named trait is exhibited. Utilitarianism shuffles activity versus baseline with a per-item RNG seed and asks if Scenario 1 is preferable. training_split is declared but scoring uses test. Hard Test CSVs exist in the authors' tarball; the EleutherAI loader comments that the hard splits are not implemented and does not emit them.

Models reporting this benchmark

No model card in ModelSpec reports this benchmark yet.

Data

This page as JSON · Edit on GitHub