BEGIN:VCALENDAR
VERSION:2.0
METHOD:PUBLISH
CALSCALE:GREGORIAN
PRODID:-//WordPress - MECv7.38.2//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&#039;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-65dfa16ba6de9bdb34ea435c9fe2a425@clt.uab.cat
DTSTART;TZID=Europe/Madrid:20261204T153000
DTEND;TZID=Europe/Madrid:20261204T170000
DTSTAMP:20261118T115125Z
CREATED:20261118
LAST-MODIFIED:20261118
PRIORITY:5
SEQUENCE:1
TRANSP:OPAQUE
SUMMARY:Nikoleta Pantelidou (UAB): ‘The gradual emergence of the grammatical inventories of Large Language Models (LLMs)’
DESCRIPTION:Seminari del CLT\nDivendres, 4 de desembre de 2026\nHora 15:30\nAula 201, Facultat de Filosofia i Lletres\nEnllaç Teams\nAbstract :\nWhile Large Language Models (LLMs) perform remarkably well on a wide range of linguistic tasks, most evaluations focus on their synchronic grammatical competence rather than on whether their linguistic «growth» brings along processes associated with language evolution. This talk explores whether LLMs exhibit patterns of change consistent with gradual grammaticalization, a fundamental process in human language change through which lexical items gradually develop grammatical functions, leading to richer grammatical inventories. The focus is on whether more elaborate grammatical inventories emerge in newer and larger models. To investigate this question, 24 frontier LLMs varying in size and release date were prompted to generate essays under a baseline condition and a condition encouraging grammatically complex language. Their grammatical inventories were then compared across models and against a matched corpus of human-authored essays. The results show that larger and newer models produce more grammatical markers overall, suggesting that model scaling and release date contribute to the development of more human-like grammatical inventories. At the same time, model inventories remain underdeveloped compared to humans in certain domains, suggesting that the parallels drawn between human and model growth do not entail convergence.\nSpeaker’s profile: https://clt.uab.cat/nikoleta-pantelidou/ ( https://clt.uab.cat/nikoleta-pantelidou/ )\n
URL:https://clt.uab.cat/activitats_clt/seminari-20261204/
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/2025/10/photo-jpg-1.jpg
END:VEVENT
END:VCALENDAR
