Papers with cultural representations

2 papers
Connecting a French Dictionary from the Beginning of the 20th Century to Wikidata (2022.lrec-1)

Copied to clipboard

Challenge: The Petit Larousse illustré is a French dictionary first published in 1905 . its value remains intact, but some descriptions are more historical than contemporary . wikidata identifiers can be used to identify, compare, and verify historically-situated representations .
Approach: They propose a wikidata-based annotation of the Petit Larousse illustré entries from 1905 . they link the entries to current data sources and use them to extract, complement, and process knowledge.
Outcome: The proposed lexical resource connects dictionary entries from 1905 to current data sources.
From Surveys to Narratives: Rethinking Cultural Value Adaptation in LLMs (2025.emnlp-main)

Copied to clipboard

Challenge: Adapting cultural values in Large Language Models presents significant challenges due to biases and data limitations.
Approach: They propose to augment World Values Survey (WVS) data with encyclopedic and scenario-based cultural narratives from Wikipedia and NormAd to address these limitations.
Outcome: The proposed approach enhances cultural distinctiveness and improves classification performance across cultures.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations