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:20260202T201248Z
LOCATION:Second Floor Atrium
DTSTART;TZID=America/Chicago:20251120T080000
DTEND;TZID=America/Chicago:20251120T170000
UID:submissions.supercomputing.org_SC25_sess533_post261@linklings.com
SUMMARY:Chameleon Concierge: Retrieval-Augmented Generation (RAG) To Enhan
 ce Open Testbed Documentation
DESCRIPTION:Saieda Ali Zada (University of Delaware)\n\nResearchers in hig
 h performance computing (HPC) and cloud environments encounter disparate s
 ources of documentation and difficulties finding accurate information. Thi
 s can cause inefficiency, increase the reliance on support teams, and chan
 ge the focus of the researcher from the main experiment. To address these 
 challenges, we developed an AI-powered search system leveraging large lang
 uage models (LLMs) with retrieval-augmented generation (RAG) to unify vari
 ous documentation sources and provide accurate, context-aware answers with
  cited references to relevant sources. We evaluated our RAG system with Ch
 ameleon Cloud testbed documentation as a case study, finding that our RAG 
 system outperforms other generic LLMs in answering a variety of user quest
 ions and performs comparable to proprietary LLMs when properly tuned and o
 ptimized.\n\nTag: Research & ACM SRC Posters\n\nRegistration Category: Tec
 hnical Program Reg Pass\n\nSession Chairs: Kento Sato (RIKEN Center for Co
 mputational Science (R-CCS)); Chris Schlipalius (Pawsey Supercomputing Res
 earch Centre; Commonwealth Scientific and Industrial Research Organisation
  (CSIRO), Australia); and Anja Gerbes (Georg-August-Universität Göttingen)
 \n\n
END:VEVENT
END:VCALENDAR