Teaching a teachable agent via paraphrased natural language produces no significantly different learning gains compared to teaching via sentence-selection over a fixed interaction¶
Claim · All claims
Evidence · 1 study · causalr2·q3
Currency · newest study 2025 · not yet checked against its sources · not reviewed by a person
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? Gain scores did not differ significantly between the natural language condition (M = 5.33, SD = 3.34) and the sentence-selection condition (M = 5.61, SD = 3.74). → 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 · r2
Within-subjects user study (46 adults, counterbalanced order) comparing teaching modalities in the Curiosity Notebook on rock classification. A two-way repeated measures ANOVA found "no significant difference in gain scores between conditions F(1, 39) = 0.925, p = .342". Hypothesis H1 was not supported.
"The results showed that there was no significant difference in gain scores between conditions F(1, 39) = 0.925, p = .342. Participants in the sentence-selection con- dition gained slightly more, M = 5.61 (SD = 3.74) points, compared to the natural language condition, M = 5.33(SD = 3.34) points."
Discussion¶
Related Claims¶
- A higher proportion of taught features is learned when teaching via natural language compared to sentence-selection — 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 — possibly the same claim (merge candidate)
- A higher proportion of untaught features is learned when teaching via sentence-selection compared to natural language — related
- The amount of paraphrasing users engage in during natural language teaching is positively related to improved learning outcomes — related
Page metadata
| Field | Value |
|---|---|
type |
claim |
id |
nl-teaching-no-gain-advantage-over-sentence-selection |
title |
Teaching a teachable agent via paraphrased natural language produces no significantly different learning gains compared to teaching via sentence-selection over a fixed interaction |
description |
Teaching a teachable agent via paraphrased natural language produces no significantly different learning gains compared to teaching via sentence-selection over a fixed interaction |
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.