AI Tutors vs. Tenacious Myths: Personalised Dialogue for Misconception Correction

Synthesis: Corbett & Tangen (2026) test whether personalised AI dialogue can correct deeply held misconceptions ("tenacious myths") in psychology and education. In a preregistered experiment (N = 375), participants holding strong misconceptions engaged in one of three interventions: personalised Misconception AI Dialogue targeting their specific belief, generic Textbook-style Refutation (a refutation text), or Neutral AI Dialogue (control). Personalised Misconception AI Dialogue produced significantly larger immediate belief reductions than both Textbook Refutation and Neutral AI Dialogue; this advantage persisted at 10-day follow-up but diminished by 2 months, where Misconception AI Dialogue and Textbook Refutation converged while both remained superior to control. Both AI conditions generated significantly higher engagement and confidence than Textbook Refutation reading, showing the motivational benefits of conversational interaction.

Key Findings

• Personalised AI dialogue beats generic refutation — initially. Personalised Misconception AI Dialogue produced significantly larger immediate belief reductions than both Textbook-style Refutation and Neutral AI Dialogue, disrupting the cognitive processes that maintain misconceptions.
• The advantage fades over time. The personalised-dialogue advantage persisted at 10-day follow-up but diminished by 2 months, where Misconception AI Dialogue and Textbook Refutation converged — both still superior to control. This suggests brief interventions require spaced reinforcement for lasting change.
• AI conditions are more engaging and confidence-building. Both AI conditions generated significantly higher engagement and confidence than reading a Textbook Refutation, highlighting the motivational benefits of conversational interaction.
• Refutation texts still work. Textbook-style refutation remained superior to control at all time points — confirming the effectiveness of the refutation text technique even when outshone on immediacy by personalised dialogue.

Implications for AI in Education

The paper positions conversational AI tutors as a scalable way to deliver personalised refutation/misconception interventions that outperform static text on immediacy and motivation — but cautions that the initial advantage requires reinforcement to last. For practice, this implies integrating AI dialogue into structured programs with spaced reinforcement rather than relying on one-off interactions. It connects to the knowledge base's Misconceptions concept (misconceptions about and within AI learning), AI tutoring, and the Cognitive Offloading/belief-correction literature, and pairs with studies comparing AI dialogue vs. conceptual-change text (e.g., Akdoğan 2025, which found the reverse in science education).

Connected Concepts

• Refutation Text
• Misconceptions
• Intelligent Tutoring
• Generative AI

Connected Articles

• Akdogan Heat Temperature Conceptual Change Thesis 2025 — Comparing expert-written vs. AI-generated conceptual change text vs. interactive AI dialogue
• AI Learning Companions Framework — AI companions and misconception correction
• Critical GenAI Use Predictors — Recommends refutation texts to target conceptual misconceptions

Citation

Corbett, B. J., & Tangen, J. M. (2026). AI tutors vs. tenacious myths: Evidence from personalised dialogue interventions in education. Computers in Human Behavior, 175, 108828.