BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//CERN//INDICO//EN
BEGIN:VEVENT
SUMMARY:Veliki jezikovni modeli in domensko prilagojena UI za slovenski km
 etijski sektor | Large language models and domain-specific AI for the Slov
 enian agricultural sector
DTSTART:20261120T090000Z
DTEND:20261120T130000Z
DTSTAMP:20261104T012800Z
UID:indico-event-4028@indico.ijs.si
CONTACT:events@slaif.si
DESCRIPTION:Speakers: Marko Debeljak (Jožef Stefan Institute (JSI))\n\nIz
 vajalec / Course provider: Jožef Stefan Institute (JSI)Predavatelji / Ins
 tructors: Marko Debeljak (JSI)Content: The event aims to provide agricult
 ural stakeholders with a clear\, realistic\, and application-oriented unde
 rstanding of large language models (LLMs) and their potential role in Slov
 enian agriculture. Participants will be introduced to the rationale for fo
 cusing on high-quality\, domain-specific data and benchmarks rather than i
 ndividual model versions\, and to the role of the national AI infrastructu
 re (SLAIF) in supporting domain- and language-specific AI solutions. A key
  objective is to foster informed expectations\, trust\, and early engageme
 nt of future users by openly addressing both the capabilities and limitati
 ons of current AI technologies in regulated and practice-oriented agricult
 ural contexts.\nThe event presents current activities related to the devel
 opment and application of large language models within the Slovenian agric
 ultural domain in the context of SLAIF. It introduces the fundamentals of 
 LLMs in an accessible manner\, with a focus on their applicability\, risks
 \, and constraints in agriculture. Participants will be presented with a p
 roposed taxonomy of Slovenian agriculture\, including key sectors and subd
 omains\, along with example benchmark tasks designed to evaluate model per
 formance in Slovenian. Preliminary benchmark results will be demonstrated 
 to illustrate how existing models perform on selected agricultural use cas
 es. The event further provides a structured forum for validating assumptio
 ns about users\, use cases\, and sectoral coverage\, and introduces a dedi
 cated web application for the collection of high-quality question–answer
  pairs and other expert inputs to support model adaptation and evaluation.
 \nAfter the event\, participants will understand the importance of domain-
 specific data\, benchmarks\, and expert validation for the sustainable dev
 elopment of AI solutions in agriculture. They will have a realistic unders
 tanding of what current large language models can and cannot do in the Slo
 venian agricultural context\, and how national AI infrastructure supports 
 their adaptation. Participants will be able to critically assess proposed 
 use cases and benchmarks from a practitioner’s perspective and will be e
 quipped to contribute expert knowledge\, feedback\, and structured data in
 puts for the continued development and evaluation of AI tools for Slovenia
 n agriculture.\n\nhttps://indico.ijs.si/event/4028/
IMAGE;VALUE=URI:https://indico.ijs.si/event/4028/logo-3560331715.png
LOCATION:4. nadstropje – konferenčna dvorana (Pomurska gospodarska zbor
 nica)
URL:https://indico.ijs.si/event/4028/
END:VEVENT
END:VCALENDAR