Morality is Non-Binary: Building a Pluralist Moral Sentence Embedding Space using Contrastive Learning
Fuente:
arXiv
Guardado en:
| Autores principales: | , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866929358824800256 |
|---|---|
| author | Park, Jeongwoo Liscio, Enrico Murukannaiah, Pradeep K. |
| author_facet | Park, Jeongwoo Liscio, Enrico Murukannaiah, Pradeep K. |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2401_17228 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Morality is Non-Binary: Building a Pluralist Moral Sentence Embedding Space using Contrastive Learning Park, Jeongwoo Liscio, Enrico Murukannaiah, Pradeep K. Computation and Language Artificial Intelligence 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. |
| title | Morality is Non-Binary: Building a Pluralist Moral Sentence Embedding Space using Contrastive Learning |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2401.17228 |