The paper formalizes three types of pluralistic AI models and three benchmark classes, arguing that current alignment techniques may reduce rather than increase distributional pluralism.
Knowledge of cultural moral norms in large language models
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
representative citing papers
LLMs show accuracy drops of 0.3% to 5.9% on GSM8K math problems when culturally adapted to six countries while keeping math operations identical, with statistical significance confirmed by McNemar tests.
MEMOed framework attributes LLM generations about cultures to pretraining memorization and finds frequency-based biases across 110 cultures for food and clothing.
citing papers explorer
-
A Roadmap to Pluralistic Alignment
The paper formalizes three types of pluralistic AI models and three benchmark classes, arguing that current alignment techniques may reduce rather than increase distributional pluralism.
-
Lost in Cultural Translation: Do LLMs Struggle with Math Across Cultural Contexts?
LLMs show accuracy drops of 0.3% to 5.9% on GSM8K math problems when culturally adapted to six countries while keeping math operations identical, with statistical significance confirmed by McNemar tests.
-
Attributing Culture-Conditioned Generations to Pretraining Corpora
MEMOed framework attributes LLM generations about cultures to pretraining memorization and finds frequency-based biases across 110 cultures for food and clothing.