BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Drupal iCal API//EN
X-WR-CALNAME:Events items teaser
X-WR-TIMEZONE:America/Toronto
BEGIN:VTIMEZONE
TZID:America/Toronto
X-LIC-LOCATION:America/Toronto
BEGIN:DAYLIGHT
TZNAME:EDT
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
DTSTART:20230312T070000
END:DAYLIGHT
BEGIN:STANDARD
TZNAME:EST
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
DTSTART:20231105T060000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
UID:69d0bedaa7a8c
DTSTART;TZID=America/Toronto:20231113T120000
SEQUENCE:0
TRANSP:TRANSPARENT
DTEND;TZID=America/Toronto:20231113T130000
URL:https://uwaterloo.ca/computer-science/events/phd-seminar-artificial-int
 elligence-unraveling-the-dilemma-of-ai-errors
LOCATION:200 University Avenue West Online PhD seminar Waterloo ON N2L 3G1 
 Canada
SUMMARY:PhD Seminar • Artificial Intelligence • Unraveling the Dilemma 
 of\nAI Errors: Exploring the Effectiveness of Human and Machine\nExplanati
 ons for Large Language Models
CLASS:PUBLIC
DESCRIPTION:PLEASE NOTE: THIS PHD SEMINAR WILL TAKE PLACE ONLINE.\n\nMARVIN
  PAFLA\, PHD CANDIDATE\n_David R. Cheriton School of Computer Science_\n\n
 SUPERVISORS: Professors Kate Larson\, Mark Hancock\n\nWith the rise of lar
 ge language models (LLMs) like GPT\, the field of\neXplainable artificial 
 intelligence (XAI) has exploded and produced a\nplethora of methods  (e.g
 .\, saliency-maps) to gain insight into deep\nneural nets. However\, human
 -participant studies question the efficacy\nof these methods\, particularl
 y when the AI output is wrong.
DTSTAMP:20260404T073346Z
END:VEVENT
END:VCALENDAR