Socratic feedback is associated with higher task orientation and comprehension monitoring than directive feedback; on feedback regulation it has no main effect, but its effect depends on agent type¶

Claim · All claims
Evidence · 1 study (2 entries) · causal r? · q3 · i2–i3
Currency · newest study 2026 · checked against its sources 2026-10-19 (automated, 2 of 2 entries) · not reviewed by a person

Subclaims¶

q3 i3 Feedback style showed a significant main effect on comprehension monitoring, with higher scores under Socratic feedback (large effect). → Han Xue 2026 q3 i2 Feedback style showed a significant main effect on task orientation, with higher scores under Socratic feedback (moderate effect). → Han Xue 2026 q3 i2 A significant agent type × feedback style interaction emerged for feedback regulation. → Han Xue 2026 (2)

Evidence¶

Han Xue 2026¶

Han Xue, Cao Jing, Wang Zi, Luo Heng. (2026). The Effects of Agent Type and Feedback Style on Self-Directed Learning: A Mixed-Methods Study. Behavioral Sciences. https://doi.org/10.3390/bs16071069

q3 · i3 · causal · r?

Mixed-design ANOVA of coded self-regulatory behaviors from interaction logs in the 2×2 study (51 postgraduate students). Descriptively, scores for both task orientation and comprehension monitoring were higher under Socratic than directive feedback across both agent types. No significant main effect of agent type was found for these dimensions.

"feedback style showed significant main effects on task orientation (η2p = 0.226) and comprehension monitoring (η2p = 0.339), indicating moderate to large effects."

Han Xue 2026 (2)¶

Han Xue, Cao Jing, Wang Zi, Luo Heng. (2026). The Effects of Agent Type and Feedback Style on Self-Directed Learning: A Mixed-Methods Study. Behavioral Sciences. https://doi.org/10.3390/bs16071069

q3 · i2 · causal · r?

Mixed-design ANOVA on feedback regulation ratings from the same interaction-log coding. No significant main effect of feedback style was observed for feedback regulation, but the agent type × feedback style interaction was significant (η2p = 0.078).

"However, a significant interaction effect emerged for feedback regulation (η2p = 0.078), indicating that the pattern of feedback regulation varied across the combinations of agent type and feedback style."

Discussion¶

Learner Variables¶

• Self-Regulation — outcome: instruction changes it
• Metacognition — outcome: instruction changes it

Related Claims¶

• 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) — the general claim this finding bears on, with the studies behind it

• Questioning Strategies Improve Learning — the general claim this finding bears on, with the studies behind it

• The customized agent's advantage in short-term task improvement emerges under directive feedback but not under Socratic feedback — related
• Directive feedback is associated with higher cognitive load than Socratic feedback, with no agent-type effects on learning experiences — related
• Qualitatively, Socratic prompts supported reflective monitoring while directive feedback was associated with overload and resistance — related
• As cited second-hand in an AI-literacy framework paper: ChatGPT use improved short-term essay scores but triggered metacognitive laziness with no significant knowledge-transfer gains — related
• AI TA condition shows no statistically significant differences in perceived task-comprehension support, correctness, or interaction stress — related
• Students rate the Socratic + Full Context AI TA significantly lowest for perceived support of task completion — related
• Customized AI agents generate feedback with higher accuracy and specificity than general-purpose agents in self-directed instructional design tasks — related