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:20251016T135143Z
LOCATION:Riverside East
DTSTART;TZID=America/Chicago:20251014T173000
DTEND;TZID=America/Chicago:20251014T183000
UID:HFESAM_ASPIRE 2025_sess131_POST336@linklings.com
SUMMARY:Evaluating the Impact of System Prompt Length on the Consistency a
 nd Accuracy of ChatGPT-Generated Educational Tasks
DESCRIPTION:Joseph Slade, Alina Hyk, and Regan Gurung (Oregon State Univer
 sity)\n\nThis study investigates the impact of system prompt length on the
  consistency and accuracy of ChatGPT-generated educational tasks in an int
 roductory psychology course. A custom OpenAI GPT model was used to teach t
 he Fundamental Attribution Error (FAE), but students reported inconsistenc
 ies in assignment delivery. To evaluate the model’s reliability, we develo
 ped a rubric assessing (1) adherence to prompt structure, (2) response acc
 uracy, and (3) overall interaction quality. In a classroom pilot (N = 74),
  feedback informed prompt refinements, and a subsequent study randomly ass
 igned students (N = 259) to either a long (720-word) or short (316-word) s
 ystem prompt condition. Raters will evaluate AI-student transcripts to det
 ermine whether system prompt length influenced instructional fidelity. Pre
 liminary results suggest that longer prompts may produce more accurate and
  structured responses, while shorter prompts may lead to greater variabili
 ty. This study aims to clarify whether prompt design significantly affects
  the reliability of LLM-driven instruction. Findings will inform best prac
 tices for using AI in education, emphasizing the need for validated design
  frameworks to ensure consistent learning outcomes. As AI becomes more pre
 valent in classrooms, understanding how to optimize prompt construction is
  critical for achieving scalable, high-quality instructional experiences.\
 n\n
END:VEVENT
END:VCALENDAR