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:20251016T135125Z
LOCATION:Grand Hall M/N
DTSTART;TZID=America/Chicago:20251014T165000
DTEND;TZID=America/Chicago:20251014T171000
UID:HFESAM_ASPIRE 2025_sess274_LECT397@linklings.com
SUMMARY:Aligning Pedagogy with Generative AI: An Approach to Customizing E
 ducational GPTs
DESCRIPTION:April Tan, Michael Dorneich, and Elena Cotos (Iowa State Unive
 rsity)\n\nThis study presents an approach for crafting system prompts to c
 ustomize Generative Pre-Trained Transformers (GPTs) for teaching purposes.
  As Generative AI (GenAI) becomes increasingly used as teaching tools, edu
 cators must understand GPTs limitations, operational logic, and biases to 
 create learning experiences that are helpful, honest, and harmless. Many e
 ducators often deploy default GPT models without any form of contextual tr
 aining, risking outputs that are misaligned, unreliable, or even harmful. 
 To address this, the study provides an approach for educators to systemati
 cally train and evaluate customized GPTs for their own educational context
 s. This approach translates pedagogical theories, learning objectives, and
  instructional strategies into structured prompts and curated knowledge ba
 ses. A case study illustrates how this approach was used to customize a GP
 T to teach the rhetorical goals of research writing. The customized GPT de
 monstrated a stronger pedagogy, persona, contextual awareness, and objecti
 ve alignment compared to the default GPT model; however, it still violated
  key rules under adversarial queries. This study provides mitigation recom
 mendations for structuring and refining system prompts to strengthen GPT c
 ompliance. By offering an accessible way to customize GPTs without complex
  technical interventions, this framework allows educators to leverage thei
 r expertise while mitigating risks and biases.\n\nTrack: Training\n\nSessi
 on Chair: Saman Madinei (The Boeing Company)\n\n
END:VEVENT
END:VCALENDAR