BEGIN:VCALENDAR
VERSION:2.0
PRODID:icalendar-ruby
CALSCALE:GREGORIAN
BEGIN:VTIMEZONE
TZID:America/Chicago
BEGIN:DAYLIGHT
DTSTART:20260308T030000
TZOFFSETFROM:-0600
TZOFFSETTO:-0500
RRULE:FREQ=YEARLY;BYDAY=2SU;BYMONTH=3
TZNAME:CDT
END:DAYLIGHT
BEGIN:STANDARD
DTSTART:20251102T010000
TZOFFSETFROM:-0500
TZOFFSETTO:-0600
RRULE:FREQ=YEARLY;BYDAY=1SU;BYMONTH=11
TZNAME:CST
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP;TZID=America/Chicago:20260407T151759
UID:218129@calendar.wisc.edu
DTSTART;TZID=America/Chicago:20260209T120000
DTEND;TZID=America/Chicago:20260209T130000
DESCRIPTION:Large language models can hold remarkably fluent conversations\
 , and they make things up. These "hallucinations" (or\, more accurately\, 
 confabulations) are among the biggest challenges to building trustworthy A
 I systems. This talk\, part of UW-Madison's 2026 Love Data Week\, explores
  why these errors occur\, how to spot them\, and introduces practical stra
 tegies for reducing them.\n\nCONTACT: 414-803-9830\, dapir@provost.wisc.ed
 u\n\nURL: https://data.wisc.edu/love-data-week/#love-data-week-events\n\nO
 NLINE: https://data.wisc.edu/event/hallucination-in-the-wild-a-field-guide
 -for-llm-users/
LOCATION:  (Online)
SUMMARY:Hallucination in the Wild: A Field Guide for LLM Users
URL;VALUE=URI:https://data.wisc.edu/love-data-week/#love-data-week-events
END:VEVENT
END:VCALENDAR