BEGIN:VCALENDAR
VERSION:2.0
METHOD:PUBLISH
CALSCALE:GREGORIAN
PRODID:-//WordPress - MECv7.33.0//EN
X-ORIGINAL-URL:https://clt.uab.cat/
X-WR-CALNAME:CLT Centre de Lingüística Teòrica
X-WR-CALDESC:Grup de Recerca Consolidat Gran des del 1993 i reconegut com a Centre d'Estudis i Recerca de la UAB el 2006.
X-WR-TIMEZONE:Europe/Madrid
BEGIN:VTIMEZONE
TZID:Europe/Madrid
X-LIC-LOCATION:Europe/Madrid
BEGIN:DAYLIGHT
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
TZNAME:CEST
DTSTART:20260329T030000
RRULE:FREQ=YEARLY;BYMONTH=03;BYDAY=-1SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
TZNAME:CET
DTSTART:20261025T020000
RRULE:FREQ=YEARLY;BYMONTH=10;BYDAY=4SU
END:STANDARD
END:VTIMEZONE
REFRESH-INTERVAL;VALUE=DURATION:PT1H
X-PUBLISHED-TTL:PT1H
X-MS-OLK-FORCEINSPECTOROPEN:TRUE
BEGIN:VEVENT
CLASS:PUBLIC
UID:MEC-a9dab015b5ebf6fce8c88e0d387c057d@clt.uab.cat
DTSTART;TZID=Europe/Madrid:20260123T153000
DTEND;TZID=Europe/Madrid:20260123T170000
DTSTAMP:20260116T093125Z
CREATED:20260116
LAST-MODIFIED:20260119
PRIORITY:5
SEQUENCE:2
TRANSP:OPAQUE
SUMMARY:Natalia Moskvina (UAB) ‘Multilingual Variation in Language Comprehension in Large Language Models’
DESCRIPTION:Seminari del CLT\nDivendres, 23 de gener de 2026\nHora 15:30\nAula 202\nEnllaç Teams\nAbstract:\nWith recent advances in Artificial Intelligence (AI) tools and Large Language Models (LLMs) in particular, a growing number of people are turning to these systems for professional or personal assistance. This increasing influence calls for a thorough evaluation of their abilities in order to ensure safe and ethical use. Previous research demonstrated that LLMs still struggle to reach a human-like level of performance in a range of language aspects (e.g., Qiu et al., 2023; Collacciani et al., 2024; Dentella et al., 2024). However, while models are trained and prompted in a variety of natural languages, it remains unexplored how their linguistic abilities vary across them, with the majority of studies focusing on English as the assumed dominant language of LLMs (Zhang et al., 2023). Our study aims to explore LLMs’ multilingual performance by evaluating their language comprehension across 12 diverse languages: English, German, Dutch, Spanish, Italian, Catalan, Greek, Russian, Turkish, Arabic, Chinese, and Japanese. The results show significant cross-linguistic variation in the accuracy of models’ responses, however, in contrast with previous findings, LLMs did not exhibit superior performance in English, while Spanish and Italian did score consistently high for all tested models. Additionally, humans significantly outperformed models across languages, with the exception of Spanish for GPT-4o and Italian for DeepSeek-V3, where they demonstrated a comparable level of language comprehension. The findings open the discussion about the reliability of models’ multilingual use as well as the challenges posed by different language systems.\n
URL:https://clt.uab.cat/activitats_clt/moskvina-seminari-230126/
ORGANIZER;CN=Centre de Lingüística Teòrica:MAILTO:cr.clt@uab.cat
CATEGORIES:Seminaris
LOCATION:Campus UAB, Bellaterra (Barcelona)
ATTACH;FMTTYPE=image/jpeg:https://clt.uab.cat/wp-content/uploads/2025/09/Natalia-Moskvina.jpg
END:VEVENT
END:VCALENDAR