The question of how to make decisions that maximise the well-being of all persons is very relevant to design language models that are beneficial to humanity and free from harm. We introduce the Greatest Good Benchmark to evaluate the moral judgments of LLMs using utilitarian dilemmas. Our analysis across 15 diverse LLMs reveals consistently encoded moral preferences that diverge from established moral theories and lay population moral standards. Most LLMs have a marked preference for impartial beneficence and rejection of instrumental harm. These findings showcase the 'artificial moral compass' of LLMs, offering insights into their moral alignment.
The Greatest Good Benchmark: Measuring LLMs' Alignment with Utilitarian Moral Dilemmas
Evaluation of moral judgments in language models using utilitarian dilemmas reveals divergences from human moral standards, highlighting their 'artificial moral compass.'
- Year
- 2025
- Venue
- arXiv 2025
- Authors
- 6
- Hosting
- Abstract onlyARXIV-DEFAULT
Cite
Notes
Only stored in your browser.
Attribution
- Abstract & full text
- arxiv.org/abs/2503.19598ARXIV-DEFAULT
- TL;DR
- Semantic Scholar