2 papers
cs.AI2026
The Scaffold Effect: How Prompt Framing Drives Apparent Multimodal Gains in Clinical VLM Evaluation
Doan Nam Long Vu, Simone Balloccu
Trustworthy clinical AI requires that performance gains reflect genuine evidence integration rather than surface-level artifacts. We evaluate 12 open-weight vision-language models…
cs.CL2025
Roleplaying with Structure: Synthetic Therapist-Client Conversation Generation from Questionnaires
Doan Nam Long Vu, Rui Tan, Lena Moench +9
The development of AI for mental health is hindered by a lack of authentic therapy dialogues, due to strict privacy regulations and the fact that clinical sessions were historicall…