Socratic-mode participants progressively disengaged from the chatbot: message counts declined after question 5 and EEG engagement fell to its lowest value at question 10¶

Claim · All claims
Evidence · 1 study · causal r2 · q2
Currency · newest study 2026 · not yet checked against its sources · not reviewed by a person

Subclaims¶

q2 i? In the Socratic condition, the mean number of chat messages per question declined after Q5, and EEG engagement dropped to E_norm = 0.297 at Q10, well below the 0.5 baseline. → Alexandre Clin Deffarges 2026

Evidence¶

Alexandre Clin Deffarges 2026¶

Alexandre Clin Deffarges, Nataliya Kosmyna, and Pattie Maes. (2026). Socrates went Nuclear: Comparing Interaction Strategies for AI systems in a Learning Context using Brain Sensing. arXiv preprint arXiv:2609.00584. https://arxiv.org/abs/2609.00584 doi:10.48550/arxiv.2609.00584

q2 · i? · causal · r2

Behavioral and neurophysiological analysis of the Socratic condition during the training phase. Mode 2 participants exchanged far more messages overall (M=119.2, SD=50.2) than Mode 1 (M=37.3, SD=19.8), but the per-question message count declined after Q5 while EEG engagement fell to its lowest point at Q10. The authors state the two independent measures indicate participants who expected direct answers progressively abandoned the chatbot.

"This behavioral disengagement in Mode 2 converges with the EEG data: the Socratic mode's EEG engagement drops to its lowest point at Q10 (𝐸norm = 0.297, well below the 0.5 baseline)."

Discussion¶

Related Claims¶

• Questioning Strategies Improve Learning — the general claim this finding bears on, with the studies behind it
• The EEG-adaptive exercise condition produced significantly higher cognitive engagement during training than the unrestricted chatbot condition (p = .018), and was the only condition above the 0.5 baseline — related
• In an immediate post-test design, participants with an unrestricted chatbot achieved significantly higher learning deltas than participants with a Socratic chatbot (d = 0.80) or an EEG-adaptive exercise system (d = 0.85) — related
• Socratic + No Context produces the highest query volume and Direct + No Context the longest messages — related
• Most unrestricted-mode interactions were direct answer retrieval: 52.9% of exercise interactions were copy-paste of the question, and participant answers were linguistically near-identical to chatbot text in 25.3% of cases — related