Delayed retention shows no clear difference between LLM-based and traditional teaching (SMD 0.15)¶

Claim · All claims
Evidence · 1 study · quant-synthesis r2 · q3
Currency · newest study 2026 · not yet checked against its sources · not reviewed by a person

Subclaims¶

q3 i? Across 2 studies (66 vs. 82 participants), delayed retention showed no clear difference between LLM-based and traditional teaching (SMD 0.15, 95% CI -0.50 to 0.80). → Liu Xiaoliu 2026

Evidence¶

Liu Xiaoliu 2026¶

Liu Xiaoliu, Pan Jiayue, Zhang Chengyi, Wang Xiaomei, Wan Jinghua, Wang Qiang. (2026). Effectiveness of large language model-based teaching interventions in medical education: a systematic review and stratified meta-analysis of 14 studies. BMC Medical Education. https://doi.org/10.1186/s12909-026-09879-0

q3 · i? · quant-synthesis · r2

Supplementary random-effects meta-analysis of 2 delayed post-intervention retention studies (66 vs. 82 participants). The pooled SMD of 0.15 crossed the null (95% CI -0.50 to 0.80); GRADE-informed certainty was very low. Equivalence was not tested.

"Delayed retention included 2 studies (66 vs. 82 participants; Fig. 5), with a pooled effect of SMD 0.15 (95% CI -0.50 to 0.80)."

Discussion¶

Related Claims¶

• Strict knowledge acquisition shows a smaller positive pooled signal for LLM-based teaching (SMD 0.80) — related
• LLM-based teaching is associated with higher post-course score-based outcomes than non-AI teaching in an exploratory pooled synthesis (SMD 0.90), with very high heterogeneity — related
• Structured clinical performance shows the largest pooled signal (SMD 3.39) but rests on a very small evidence base — related