English

An Evaluation of GPT-4 on the ETHICS Dataset

Computation and Language 2023-09-20 v1 Artificial Intelligence

Abstract

This report summarizes a short study of the performance of GPT-4 on the ETHICS dataset. The ETHICS dataset consists of five sub-datasets covering different fields of ethics: Justice, Deontology, Virtue Ethics, Utilitarianism, and Commonsense Ethics. The moral judgments were curated so as to have a high degree of agreement with the aim of representing shared human values rather than moral dilemmas. GPT-4's performance is much better than that of previous models and suggests that learning to work with common human values is not the hard problem for AI ethics.

Keywords

Cite

@article{arxiv.2309.10492,
  title  = {An Evaluation of GPT-4 on the ETHICS Dataset},
  author = {Sergey Rodionov and Zarathustra Amadeus Goertzel and Ben Goertzel},
  journal= {arXiv preprint arXiv:2309.10492},
  year   = {2023}
}

Comments

8 pages