In the AVP, per-turn disclosure change responds to trainee exploration but not measurably to trainee empathy, and the static baseline shows no significant joint response¶

Claim · All claims
Evidence · 1 study · design r2 · q2
Currency · newest study 2026 · checked against its sources 2026-10-17 (automated, 1 of 1 entry) · not reviewed by a person

Subclaims¶

q2 i? OLS regression of per-turn disclosure change found exploration drove AVP state change while the empathy coefficient was effectively zero; in the static VP exploration was only marginal and the joint model not significant. → Angela Chen 2026

Evidence¶

Angela Chen 2026¶

Angela Chen, Siwei Jin, Catherine Bao, Canwen Wang, Robert E. Kraut, Tongshuang Wu, and Haiyi Zhu. (2026). The Empirically Grounded Adaptive Virtual Patient for Psychotherapy Training: Disclosure That Responds to Therapist Micro-Skills. https://arxiv.org/abs/2606.10051 doi:10.48550/arxiv.2606.10051

q2 · i? · design · r2

OLS regression with cluster-robust SEs on session (530 turn-pairs, 40 AVP sessions; 423 turn-pairs, 40 SVP sessions) of evaluated disclosure change on empathy total and exploration. The quote shows "exploration drives the change ( ˆβexp = +0.281"; the exploration coefficient is positive and significant, but it is unstandardized and no standardized effect size is printed, so the magnitude is coded i?.

"In A VP, exploration drives the change ( ˆβexp = +0.281 , p<10 −6) while the empathy coefficient is effectively zero (ˆβemp = +0.004,p=.87 )"

Discussion¶

Learner Variables¶

• Social Awareness and Relationship Skills — predictor: learners who differ on it differ in outcomes

Related Claims¶

• The adaptive virtual patient produces a steadily climbing disclosure trajectory across a session while a prompt-only baseline with the same LLM and persona stays flat — related
• The AVP's generated text matches its intended internal disclosure level about twice as often as the static baseline (0.651 vs. 0.311 agreement) — related
• Higher-skill trainees elicit faster-climbing AVP disclosure trajectories, directionally supporting skill sensitivity, though the formal interaction test is underpowered — related
• The deployed empirically motivated weight vector outperforms equal, empathy-only, and exploration-only weightings in evaluator agreement, with exploration carrying most of the adaptive signal — related
• Post-session subjective ratings favored the adaptive system for the expressive persona but showed a reversed adaptivity disadvantage for the guarded persona — related
• Expert evaluation found the virtual patient realistic and immediate ACT feedback increased therapists' awareness of intervention choices — related
• In a self-selected survey, students favored delayed disclosure and agency, but 39.3% found the system too indirect and 42.9% reported repetition — related