A higher proportion of taught features is learned when teaching via natural language compared to sentence-selection¶
Claim · All claims
Evidence · 1 study · causalr1·q3
Currency · newest study 2025 · not yet checked against its sources · not reviewed by a person
Design limits · Rachel Love 2025: the intervention came bundled with another change (read from the study by two models, 2026-10-27)
Subclaims¶
Reading the evidence codes
q is the design tier, i the impact, n the sample, and the kind with its r
the rigour judged within that kind: what each code means.
This claim: no standardized effect is recorded in observations/ for it yet, so no benchmark reading is possible.
q3 i? Participants in the natural language condition learned a significantly higher proportion of the features they taught (M = 50%) compared to sentence-selection (M = 41.6%). → Rachel Love 2025
Evidence¶
Rachel Love 2025¶
Rachel Love, Edith Law, Philip R. Cohen, Dana Kulić. (2025). Teaching a Conversational Agent using Natural Language: Effect on Learning and Engagement. Int J Artif Intell Educ. https://doi.org/10.1007/s40593-025-00461-1
q3 · i? · causal · r1
Exploratory two-way repeated measures ANOVA on the proportion of taught features answered correctly at post-test but not pre-test. The natural language condition showed a significantly higher proportion learned, which "may indicate that this teaching modality improves recall of content that was covered".
"participants in the natural language condition learned significantly more of the features they taught compared to sentence-selection (natural language: M = 50% (SD = 21.9); sentence- selection: M = 41.6% (SD = 21.7)), F(1, 39) = 4.176, p = .048."
Discussion¶
Related Claims¶
- A higher proportion of untaught features is learned when teaching via sentence-selection compared to natural language — related
- Natural language teaching takes significantly longer per input and yields significantly fewer teaching attempts and fewer features taught than sentence-selection — related
- Teaching a teachable agent via paraphrased natural language produces no significantly different learning gains compared to teaching via sentence-selection over a fixed interaction — reports the opposite
- Teaching via paraphrased natural language is perceived as more helpful for learning than sentence-selection, but this perception is not reflected in actual learning gains — reports the opposite
Page metadata
| Field | Value |
|---|---|
type |
claim |
id |
nl-higher-proportion-taught-features-learned |
title |
A higher proportion of taught features is learned when teaching via natural language compared to sentence-selection |
description |
A higher proportion of taught features is learned when teaching via natural language compared to sentence-selection |
status |
review |
evidence_strength |
moderate |
newest_evidence |
2025 |
generated |
by process:wiki-ingest on 2026-10-27 |
trust |
unverified — no one has confirmed this page's content |
sources |
1 — rachel-love-2025 |
Frontmatter is the page's machine-readable record — see the Schema & Guide.