Facts Do Care About Your Language: Assessing Answer Quality of Multilingual LLMs

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Kansal, Yuval, Berman, Shmuel, Liu, Lydia
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913880639275008
author Kansal, Yuval
Berman, Shmuel
Liu, Lydia
author_facet Kansal, Yuval
Berman, Shmuel
Liu, Lydia
contents Factuality is a necessary precursor to useful educational tools. As adoption of Large Language Models (LLMs) in education continues of grow, ensuring correctness in all settings is paramount. Despite their strong English capabilities, LLM performance in other languages is largely untested. In this work, we evaluate the correctness of the Llama3.1 family of models in answering factual questions appropriate for middle and high school students. We demonstrate that LLMs not only provide extraneous and less truthful information, but also exacerbate existing biases against rare languages.
format Preprint
id arxiv_https___arxiv_org_abs_2506_03051
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Facts Do Care About Your Language: Assessing Answer Quality of Multilingual LLMs
Kansal, Yuval
Berman, Shmuel
Liu, Lydia
Computation and Language
Artificial Intelligence
Factuality is a necessary precursor to useful educational tools. As adoption of Large Language Models (LLMs) in education continues of grow, ensuring correctness in all settings is paramount. Despite their strong English capabilities, LLM performance in other languages is largely untested. In this work, we evaluate the correctness of the Llama3.1 family of models in answering factual questions appropriate for middle and high school students. We demonstrate that LLMs not only provide extraneous and less truthful information, but also exacerbate existing biases against rare languages.
title Facts Do Care About Your Language: Assessing Answer Quality of Multilingual LLMs
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2506.03051