BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:America/Chicago
X-LIC-LOCATION:America/Chicago
BEGIN:DAYLIGHT
TZOFFSETFROM:-0600
TZOFFSETTO:-0500
TZNAME:CDT
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=2SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0500
TZOFFSETTO:-0600
TZNAME:CST
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=11;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20260202T201805Z
LOCATION:276
DTSTART;TZID=America/Chicago:20251116T153000
DTEND;TZID=America/Chicago:20251116T155000
UID:submissions.supercomputing.org_SC25_sess210_ws_hust103@linklings.com
SUMMARY:Generating Frequently Asked Questions from Technical Support Ticke
 ts using Large Language Models
DESCRIPTION:Christina Joslin (Purdue University), David Burns (University 
 of Wisconsin-Madison), and FNU Ashish and Elham Sarbijan (Purdue Universit
 y)\n\nHigh-performance computing drives scientific discovery, but increasi
 ng system complexity and user demands generate a growing volume of diverse
  technical support issues. This trend underscores the need for automated t
 ools that can extract clear, accurate, and relevant frequently asked quest
 ions from support tickets. We addressed this need by developing a novel pi
 peline for autonomous technical support that began by filtering tickets by
  anomaly frequency and recency. An instruction-tuned a large language mode
 l, then cleaned and summarized tickets. Next, unsupervised semantic cluste
 ring identified subclusters of similar tickets within broader topics, whic
 h were globally ranked by size, cohesion, and separation. A generation mod
 ule powered by a large language model produced structured lists of frequen
 tly asked questions from the top-ranked subclusters. Evaluation by subject
  matter experts confirmed that our method produced understandable, accurat
 e, and pertinent content.  The extraction of detailed insights from ticket
  data enhances efficiency of support workflows and facilitates scientific 
 research.\n\nRecording: Livestreamed, Recorded\n\nRegistration Category: T
 echnical Program Reg Pass, Workshop Reg Pass\n\nSession Chairs: Elsa J. Go
 nsiorowski (Lawrence Livermore National Laboratory (LLNL)); Lev Gorenstein
  (Globus, University of Chicago); Chris Bording (University of Western Aus
 tralia); Aaron P Jezghani (Georgia Institute of Technology, The Nab Collab
 oration); and Ilya Zhukov (Forschungszentrum Jülich, Jülich Supercomputing
  Centre (JSC))\n\n
END:VEVENT
END:VCALENDAR