Morality is Non-Binary: Building a Pluralist Moral Sentence Embedding Space using Contrastive Learning

Jeongwoo Park, Enrico Liscio, Pradeep Murukannaiah


Abstract
Recent advances in NLP show that language models retain a discernible level of knowledge in deontological ethics and moral norms. However, existing works often treat morality as binary, ranging from right to wrong. This simplistic view does not capture the nuances of moral judgment. Pluralist moral philosophers argue that human morality can be deconstructed into a finite number of elements, respecting individual differences in moral judgment. In line with this view, we build a pluralist moral sentence embedding space via a state-of-the-art contrastive learning approach. We systematically investigate the embedding space by studying the emergence of relationships among moral elements, both quantitatively and qualitatively. Our results show that a pluralist approach to morality can be captured in an embedding space. However, moral pluralism is challenging to deduce via self-supervision alone and requires a supervised approach with human labels.
Anthology ID:
2024.findings-eacl.45
Volume:
Findings of the Association for Computational Linguistics: EACL 2024
Month:
March
Year:
2024
Address:
St. Julian’s, Malta
Editors:
Yvette Graham, Matthew Purver
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
654–673
Language:
URL:
https://aclanthology.org/2024.findings-eacl.45
DOI:
Bibkey:
Cite (ACL):
Jeongwoo Park, Enrico Liscio, and Pradeep Murukannaiah. 2024. Morality is Non-Binary: Building a Pluralist Moral Sentence Embedding Space using Contrastive Learning. In Findings of the Association for Computational Linguistics: EACL 2024, pages 654–673, St. Julian’s, Malta. Association for Computational Linguistics.
Cite (Informal):
Morality is Non-Binary: Building a Pluralist Moral Sentence Embedding Space using Contrastive Learning (Park et al., Findings 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.findings-eacl.45.pdf
Software:
 2024.findings-eacl.45.software.zip
Video:
 https://aclanthology.org/2024.findings-eacl.45.mp4