BEGIN:VCALENDAR
VERSION:2.0
METHOD:PUBLISH
PRODID:-//Telerik Inc.//Sitefinity CMS 15.1//EN
BEGIN:VTIMEZONE
TZID:Eastern Standard Time
BEGIN:STANDARD
DTSTART:20251102T020000
RRULE:FREQ=YEARLY;BYDAY=1SU;BYHOUR=2;BYMINUTE=0;BYMONTH=11
TZNAME:Eastern Standard Time
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
END:STANDARD
BEGIN:DAYLIGHT
DTSTART:20250301T020000
RRULE:FREQ=YEARLY;BYDAY=2SU;BYHOUR=2;BYMINUTE=0;BYMONTH=3
TZNAME:Eastern Daylight Time
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
END:DAYLIGHT
END:VTIMEZONE
BEGIN:VEVENT
DESCRIPTION:Stanisław Giziński and&nbsp\;Bartosz Pieliński of the Universit
 y of Warsaw&nbsp\;will present at the January Institutional Grammar Resear
 ch Initiative (IGRI) virtual research seminar.Abstract:This presentation f
 ocuses on the innovative application of Large Language Models (LLMs) to In
 stitutional Grammar (IG) coding. It will provide a brief overview of LLMs\
 , highlighting their potential as a solution for IG coding challenges. Thi
 s presentation will argue for integrating LLMs in this domain by showing t
 he current landscape of IG research\, marked by diverse implementation str
 ategies and a lack of standardized IG-code legal text corpus. Specifically
 \, the utilization of the few-shot approach will be explored. In this meth
 od\, LLMs are conditioned with a minimal set of IG-coded examples sufficie
 nt for the automated coding of legal documents. This approach will be eval
 uated using a selection of international conventions related to cultural h
 eritage\, climate change\, and wildlife protection.
DTEND:20240109T180000Z
DTSTAMP:20260511T192919Z
DTSTART:20240109T170000Z
LOCATION:
SEQUENCE:0
SUMMARY:Application of Large Language Models to Legal Texts IG Coding
UID:RFCALITEM639141101598272809
X-ALT-DESC;FMTTYPE=text/html:<p>Stanisław Giziński and&nbsp\;Bartosz Pieliń
 ski of the University of Warsaw&nbsp\;will present at the January Institut
 ional Grammar Research Initiative (IGRI) virtual research seminar.</p><p>A
 bstract:</p><p>This presentation focuses on the innovative application of 
 Large Language Models (LLMs) to Institutional Grammar (IG) coding. It will
  provide a brief overview of LLMs\, highlighting their potential as a solu
 tion for IG coding challenges. This presentation will argue for integratin
 g LLMs in this domain by showing the current landscape of IG research\, ma
 rked by diverse implementation strategies and a lack of standardized IG-co
 de legal text corpus. Specifically\, the utilization of the few-shot appro
 ach will be explored. In this method\, LLMs are conditioned with a minimal
  set of IG-coded examples sufficient for the automated coding of legal doc
 uments. This approach will be evaluated using a selection of international
  conventions related to cultural heritage\, climate change\, and wildlife 
 protection.</p>
END:VEVENT
END:VCALENDAR