Interaction depth is not associated with immediate recall or gains once baseline knowledge is controlled¶

Claim · All claims
Evidence · 1 study · associational r1 · q2
Currency · newest study 2026 · not yet checked against its sources · not reviewed by a person

Subclaims¶

q2 i? Depth, Volume, and Pacing did not predict post-test scores or gains beyond baseline knowledge (Depth: β = −0.014, p = .728). → Vangelis Tsiligkiris 2026

Evidence¶

Vangelis Tsiligkiris 2026¶

Vangelis Tsiligkiris. (2026). What students ask matters: LLM interaction depth, task quality, and immediate recall in higher education. International Journal of Educational Technology in Higher Education. https://doi.org/10.1186/s41239-026-00617-6

q2 · i? · associational · r1

ANCOVA and gain-score OLS regressions on 22 students' immediate post-test scores. No interaction feature predicted recall or gains; the article reports no statistically significant association and equivalence was not tested. Power was limited (approximately 0.27 to detect r = 0.30).

"Across both ANCOVA (Post-test as outcome) and gain-score specifications, Depth, Volume, and Pacing did not predict post-test scores or gains once baseline knowledge was included (all p ≥ .469; Depth: β = −0.014, p = .728)."

Discussion¶

Related Claims¶

• Explanation-seeking interaction depth is positively associated with task quality beyond baseline knowledge and volume — related
• No reliable moderation of depth effects by baseline knowledge, though simple slopes suggest an exploratory pattern — related
• Scaffolding level provides no consistent additional predictive information about subsequent exam performance beyond prior achievement and observed dialogue behavior — related