Summary of Morality Is Non-binary: Building a Pluralist Moral Sentence Embedding Space Using Contrastive Learning, by Jeongwoo Park et al.
Morality is Non-Binary: Building a Pluralist Moral Sentence Embedding Space using Contrastive Learning
by Jeongwoo Park, Enrico Liscio, Pradeep K. Murukannaiah
First submitted to arxiv on: 30 Jan 2024
Categories
- Main: Computation and Language (cs.CL)
- Secondary: Artificial Intelligence (cs.AI)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary In this paper, researchers explore the nuances of moral judgment by building a pluralist moral sentence embedding space using a state-of-the-art contrastive learning approach. The team finds that a pluralist approach to morality can be captured in an embedding space, but notes that moral pluralism is challenging to deduce via self-supervision alone and requires a supervised approach with human labels. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This study shows that language models retain knowledge of deontological ethics and moral norms. The researchers develop a new way to understand morality by recognizing individual differences in moral judgment. They create an embedding space that represents different moral elements, showing how these elements are related to each other. |
Keywords
» Artificial intelligence » Embedding space » Supervised
