BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//pretalx//program.berlinbuzzwords.de//bbuzz24//speaker//WNU87J
BEGIN:VTIMEZONE
TZID:CET
BEGIN:STANDARD
DTSTART:20001029T040000
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=10
TZNAME:CET
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
END:STANDARD
BEGIN:DAYLIGHT
DTSTART:20000326T030000
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=3
TZNAME:CEST
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
END:DAYLIGHT
END:VTIMEZONE
BEGIN:VEVENT
UID:pretalx-bbuzz24-VEQGF8@program.berlinbuzzwords.de
DTSTART;TZID=CET:20240610T172000
DTEND;TZID=CET:20240610T180000
DESCRIPTION:This talk will discuss approaches to evaluate LLMs at the end-t
 o-end and task levels\, focusing on use cases such as question-answering (
 RAG). We will also cover metric selection and ways to generate datasets us
 ing LLMs.
DTSTAMP:20260608T021604Z
LOCATION:Frannz Salon
SUMMARY:Advancements in Evaluating Large Language Model Applications - Petr
  Polezhaev
URL:https://program.berlinbuzzwords.de/bbuzz24/talk/VEQGF8/
END:VEVENT
END:VCALENDAR