LlamaLo added knowledge in almost every post, mostly correct, and most posts were internally coherent¶
Claim · All claims
Evidence · 1 study · designr2·q2
Currency · newest study 2025 · not yet checked against its sources · not reviewed by a person · recheck by 2028: tool and model accuracy changes quickly
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? LlamaLo added knowledge to the discussion in almost every post, and the added knowledge was mostly correct and attuned to the claims made. → Yifat Ben-David Kolikant 2025
q2 i? 89% of LlamaLo's posts were internally coherent, conveying a perspective presented against the users'. → Yifat Ben-David Kolikant 2025
Evidence¶
Yifat Ben-David Kolikant 2025¶
Yifat Ben-David Kolikant, Omri Hadar, Asaf Salman. (2025). Talk to the machine: Unleashing the potential of AI to scale dialogic education and reduce polarization. Intern. J. Comput.-Support. Collab. Learn. https://doi.org/10.1007/s11412-025-09461-8
q2 · i? · design · r2
Content analysis of the ten LlamaLo discussions (Findings, §4.1, Fig. 3). The analysis found that "Most of the knowledge added was correct and was attuned to our claims", with 89% internal coherence across its generated posts.
"As we expected, LlamaLo added knowledge to the discussion in almost every post. Most of the knowledge added was correct and was attuned to our claims. Furthermore, most of Llamalo's posts (89%) were internally coherent, which conveyed a certain perspective that was presented against ours."
Discussion¶
Related Claims¶
- LlamaLo exhibited bias and presented contested assertions as facts, notably in the Israeli-Palestinian conflict discussion
- The fine-tuned chatbot LlamaLo extensively expanded the user's dialogic space through deepening and widening acts across ten contentious-topic discussions
- LlamaLo occasionally employed an aggressive or sarcastic tone, sometimes without user provocation, though it changed tone after being commented on
- LlamaLo's responses to social posts were solely social and it did not push back to resume the discussion
Page metadata
| Field | Value |
|---|---|
type |
claim |
id |
llamalo-knowledge-addition-coherence |
title |
LlamaLo added knowledge in almost every post, mostly correct, and most posts were internally coherent |
description |
LlamaLo added knowledge in almost every post, mostly correct, and most posts were internally coherent |
status |
review |
evidence_strength |
moderate |
newest_evidence |
2025 |
recheck_by |
2028 |
generated |
by process:wiki-ingest on 2026-10-18 |
trust |
unverified — no one has confirmed this page's content |
sources |
1 — yifat-ben-david-kolikant-2025 |
Frontmatter is the page's machine-readable record — see the Schema & Guide.