BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:America/Los_Angeles
X-LIC-LOCATION:America/Los_Angeles
BEGIN:DAYLIGHT
TZOFFSETFROM:-0800
TZOFFSETTO:-0700
TZNAME:PDT
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=2SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0700
TZOFFSETTO:-0800
TZNAME:PST
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=11;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20261012T210904Z
LOCATION:Summit Pavilion
DTSTART;TZID=America/Los_Angeles:20261021T173000
DTEND;TZID=America/Los_Angeles:20261021T183000
UID:HFESAM_ASPIRE 2026_sess257_POST379@linklings.com
SUMMARY:Augmenting LLMs with Domain Expert Mental Models to Reduce Halluci
 nations
DESCRIPTION:Boris Kovalerchuk (Central Washington University) and Brent Fe
 gley and Sylvain Bruni (Aptima, Inc.)\n\nOur research addresses a critical
  limitation of large language models (LLMs): their tendency to hallucinate
  when faced with incomplete or missing information. While techniques such 
 as Retrieval-Augmented Generation (RAG) and in-context learning improve fa
 ctual grounding, they remain insufficient when key knowledge resides only 
 in the minds of domain experts or when novel problems lack historical data
 .\nTo overcome this gap, we propose augmenting LLMs with Expert Mental Mod
 els (EMMs), computational representations of domain expertise derived thro
 ugh structured human–machine dialogue. Grounded in monotone Boolean and k-
 valued function theory, the approach systematically captures decision-rele
 vant factors, organizes them hierarchically, and encodes them into prompts
  that guide LLM reasoning. This method transforms implicit expert knowledg
 e into explicit, reusable structures that improve interpretability and red
 uce hallucinations.\nA case study using Perplexity AI demonstrates the app
 roach in the context of research proposal decision-making. Results show th
 at while LLMs can generate useful question sets and hierarchical structure
 s, expert refinement remains essential to address gaps and ensure decision
  relevance. Integrating EMMs enhances the quality of generated outputs and
  supports more reliable, explainable decision-making.\nOur work highlights
  a path forward for combining human expertise with generative AI, enabling
  more robust, transparent, and context-aware decision support systems.\n\n
END:VEVENT
END:VCALENDAR