Papers by Aida Ramezani
An unsupervised framework for tracing textual sources of moral change (2021.findings-emnlp)
Copied to clipboard
| Challenge: | Existing studies on moral sentiment classification and temporal inference of moral sentiment have not quantified the origins of these changes. |
| Approach: | They propose an unsupervised framework for tracing textual sources of moral change toward entities through time. |
| Outcome: | The proposed framework captures fine-grained human moral judgments and identifies coherent source topics of moral change triggered by historical events. |
Knowledge of cultural moral norms in large language models (2023.acl-long)
Copied to clipboard
| Challenge: | Existing studies do not examine moral variation in a diverse cultural setting. |
| Approach: | They investigate whether monolingual English language models capture moral variation across cultures . they use data from the World Values Survey and PEW global surveys . |
| Outcome: | The proposed models predict moral norms worse than the English models reported previously . the models improve inference across countries at the expense of an accurate estimate . |
The discordance between embedded ethics and cultural inference in large language models (2025.emnlp-main)
Copied to clipboard
| Challenge: | Effective interactions between AI and humans require an accurate representation of diverse cultures. |
| Approach: | They propose a framework that embeds ethical principles within an LLM and a hyperplane that embedding cultural norms within it. |
| Outcome: | The proposed framework shows that cultural norms are more aligned with ethical principles than standard models. |