SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2404.10199 · 2024

CULTURE-GEN: Revealing Global Cultural Perception in Language Models through Natural Language Prompting

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 2 functions out of this paper's own repositories and ran 2 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

RepositoryRoleRan
huihanlhh/culture-gen canonical 2 of 2
FunctionStatusWhere it lives
extract_keyword_probability_distribution Ran huihanlhh/culture-gen/script/culture_symbols.py
code served (permissive licence) · get_code("9e998932b0ab4052")
simpson_iod Ran huihanlhh/culture-gen/script/cultural_evaluations.py
code served (permissive licence) · get_code("6221576fbe8a2441")

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

As the utilization of large language models (LLMs) has proliferated world-wide, it is crucial for them to have adequate knowledge and fair representation for diverse global cultures. In this work, we uncover culture perceptions of three SOTA models on 110 countries and regions on 8 culture-related topics through culture-conditioned generations, and extract symbols from these generations that are associated to each culture by the LLM. We discover that culture-conditioned generation consist of linguistic "markers" that distinguish marginalized cultures apart from default cultures. We also discover that LLMs have an uneven degree of diversity in the culture symbols, and that cultures from different geographic regions have different presence in LLMs' culture-agnostic generation. Our findings promote further research in studying the knowledge and fairness of global culture perception in LLMs. Code and Data can be found here: https://github.com/huihanlhh/Culture-Gen/

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2404.10199")
get_code_for_paper("2404.10199")
have("2404.10199")

Connect an agent — have() is free.