Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Kazemi, Sharif, Gerhardt, Gloria, Katz, Jonty, Kuria, Caroline Ida, Pan, Estelle, Prabhakar, Umang
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2410.10489
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866929541110300672
author Kazemi, Sharif
Gerhardt, Gloria
Katz, Jonty
Kuria, Caroline Ida
Pan, Estelle
Prabhakar, Umang
author_facet Kazemi, Sharif
Gerhardt, Gloria
Katz, Jonty
Kuria, Caroline Ida
Pan, Estelle
Prabhakar, Umang
contents The training data for LLMs embeds societal values, increasing their familiarity with the language's culture. Our analysis found that 44% of the variance in the ability of GPT-4o to reflect the societal values of a country, as measured by the World Values Survey, correlates with the availability of digital resources in that language. Notably, the error rate was more than five times higher for the languages of the lowest resource compared to the languages of the highest resource. For GPT-4-turbo, this correlation rose to 72%, suggesting efforts to improve the familiarity with the non-English language beyond the web-scraped data. Our study developed one of the largest and most robust datasets in this topic area with 21 country-language pairs, each of which contain 94 survey questions verified by native speakers. Our results highlight the link between LLM performance and digital data availability in target languages. Weaker performance in low-resource languages, especially prominent in the Global South, may worsen digital divides. We discuss strategies proposed to address this, including developing multilingual LLMs from the ground up and enhancing fine-tuning on diverse linguistic datasets, as seen in African language initiatives.
format Preprint
id arxiv_https___arxiv_org_abs_2410_10489
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Cultural Fidelity in Large-Language Models: An Evaluation of Online Language Resources as a Driver of Model Performance in Value Representation
Kazemi, Sharif
Gerhardt, Gloria
Katz, Jonty
Kuria, Caroline Ida
Pan, Estelle
Prabhakar, Umang
Computation and Language
Artificial Intelligence
The training data for LLMs embeds societal values, increasing their familiarity with the language's culture. Our analysis found that 44% of the variance in the ability of GPT-4o to reflect the societal values of a country, as measured by the World Values Survey, correlates with the availability of digital resources in that language. Notably, the error rate was more than five times higher for the languages of the lowest resource compared to the languages of the highest resource. For GPT-4-turbo, this correlation rose to 72%, suggesting efforts to improve the familiarity with the non-English language beyond the web-scraped data. Our study developed one of the largest and most robust datasets in this topic area with 21 country-language pairs, each of which contain 94 survey questions verified by native speakers. Our results highlight the link between LLM performance and digital data availability in target languages. Weaker performance in low-resource languages, especially prominent in the Global South, may worsen digital divides. We discuss strategies proposed to address this, including developing multilingual LLMs from the ground up and enhancing fine-tuning on diverse linguistic datasets, as seen in African language initiatives.
title Cultural Fidelity in Large-Language Models: An Evaluation of Online Language Resources as a Driver of Model Performance in Value Representation
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2410.10489