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¶
Claim · All claims
Evidence · 1 study · causalr1·q2
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.
q2 i? Participants perceived natural language teaching as more helpful for learning, yet actual gain scores showed no significant difference between modalities. → 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
q2 · i? · causal · r1
User study with 46 adult participants teaching two virtual agents, one per modality. The article reports that "teaching by paraphrasing in natural language is perceived as being more helpful for learning" while objective gain scores did not differ significantly between conditions.
"The results indicate that teaching by paraphrasing in natural language is perceived as being more helpful for learning, but that this perception of improvement is not reflected in actual learning gain over a fixed interaction."
Discussion¶
Related Claims¶
- A higher proportion of taught features is learned when teaching via natural language compared to sentence-selection — reports the opposite
- Teaching a teachable agent via paraphrased natural language produces no significantly different learning gains compared to teaching via sentence-selection over a fixed interaction — possibly the same claim (merge candidate)
- Natural language teaching takes significantly longer per input and yields significantly fewer teaching attempts and fewer features taught than sentence-selection — related
- 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
- Students' self-reported perception of peer assessment's benefit is virtually uncorrelated with their actual measured benefit — a broader claim this one bears on
Page metadata
| Field | Value |
|---|---|
type |
claim |
id |
nl-perceived-helpful-not-reflected-in-gains |
title |
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 |
description |
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 |
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.