STELLAR
.png?apiToken=eyJhbGciOiJIUzI1NiIsImtpZCI6IjIwMjMtMDUtMDQifQ.eyJzY29wZSI6Im5vdGUtZXhwb3J0IiwibmlkIjoicUxYWGhlRGg4R1Nta2ciLCJpYXQiOjE3OTQ3MDExMTQsImlzcyI6Imh0dHBzOi8vc2xpdGUuY29tIiwianRpIjoiSTlnU3hWdEg3V0t5QWUiLCJleHAiOjE3OTcyOTMxMTR9.NxUUkiOnXjH4QH3d8wkJI85ZYNO5Z5jTydd0GilaDxo)
Steering-Vector Enhanced LLM Agents for Realistic Patient Symptom Simulations in Mental Health
Joao Sedoc · New York University (NYU) · United States
Other team members:
LDC, UPenn
- Neville Ryant
- Mark Liberman
University of Cincinnati
- Sunghye Cho
SEAS (Penn Engineering)
- Sharath Chandra Guntuku
Penn Medicine
- Raquel Gur
- Ruben Gur
- Monica Calkins
- Tyler Moore
- Monica Calkins
- Dominic Sisti
Lived Experience
- Rachel Harrison Gordon
What they're working onSTELLAR (Steering-Vector Enhanced LLM Agents for Realistic Patient Symptom Simulations in Mental Health) builds clinically faithful simulated patients for training diagnosticians and stress-testing mental-health AI. Evaluating these systems on real patients is often unsafe or impractical, and prompting alone yields simulated patients that lack clinical fidelity. Our foundational technology uses conceptors — mathematical profiles learned from real clinical interview data — to steer a language model's internal activations so it expresses symptoms of anxiety and depression realistically, adjustably, and repeatably, without retraining. On this base, we are developing digital-twin patient agents that reproduce how symptoms present in conversation, and expressive text-to-speech that gives spoken responses appropriate emotional tone. Validation combines psychometric benchmarks with clinical review.
AI approach
Large language models · LLM agents · steering vectors · symptom simulation
Mental health focus
Mental health research / simulation
Links
Research spotlight: October 2026