Danoliteracy of Generative Large Language Models

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Holm, Søren Vejlgaard, Hansen, Lars Kai, Nielsen, Martin Carsten
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866917944330551296
author Holm, Søren Vejlgaard
Hansen, Lars Kai
Nielsen, Martin Carsten
author_facet Holm, Søren Vejlgaard
Hansen, Lars Kai
Nielsen, Martin Carsten
contents The language technology moonshot moment of Generative Large Language Models (GLLMs) was not limited to English: These models brought a surge of technological applications, investments, and hype to low-resource languages as well. However, the capabilities of these models in languages such as Danish were, until recently, difficult to verify beyond qualitative demonstrations due to a lack of applicable evaluation corpora. We present a GLLM benchmark to evaluate \emph{Danoliteracy}, a measure of Danish language and cultural competency across eight diverse scenarios such as Danish citizenship tests and abstractive social media question answering. This limited-size benchmark was found to produce a robust ranking that correlates to human feedback at $ρ\sim 0.8$ with GPT-4 and Claude Opus models achieving the highest rankings. Analyzing these model results across scenarios, we find one strong underlying factor explaining $95\%$ of scenario performance variance for GLLMs in Danish, suggesting a $g$ factor of model consistency in language adaptation.
format Preprint
id arxiv_https___arxiv_org_abs_2410_22839
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Danoliteracy of Generative Large Language Models
Holm, Søren Vejlgaard
Hansen, Lars Kai
Nielsen, Martin Carsten
Computation and Language
Artificial Intelligence
Machine Learning
I.2.7
The language technology moonshot moment of Generative Large Language Models (GLLMs) was not limited to English: These models brought a surge of technological applications, investments, and hype to low-resource languages as well. However, the capabilities of these models in languages such as Danish were, until recently, difficult to verify beyond qualitative demonstrations due to a lack of applicable evaluation corpora. We present a GLLM benchmark to evaluate \emph{Danoliteracy}, a measure of Danish language and cultural competency across eight diverse scenarios such as Danish citizenship tests and abstractive social media question answering. This limited-size benchmark was found to produce a robust ranking that correlates to human feedback at $ρ\sim 0.8$ with GPT-4 and Claude Opus models achieving the highest rankings. Analyzing these model results across scenarios, we find one strong underlying factor explaining $95\%$ of scenario performance variance for GLLMs in Danish, suggesting a $g$ factor of model consistency in language adaptation.
title Danoliteracy of Generative Large Language Models
topic Computation and Language
Artificial Intelligence
Machine Learning
I.2.7
url https://arxiv.org/abs/2410.22839