LlamaLo¶
Product or Programme · All products and programmes
Evidence · 5 claims (2 for, 1 mixed, 2 against) · 1 study (1 design),q2· 0 of 1 report an effect size · 5 claims rest on one study
Description¶
LlamaLo is a dialogue chatbot fine-tuned by Yifat Ben-David Kolikant et al. from Llama-2-7b-chat-hf on Delta-awarded ChangeMyView discussions to support extended dialogue on contentious topics.
Components¶
Claims¶
- The fine-tuned chatbot LlamaLo extensively expanded the user's dialogic space through deepening and widening acts across ten contentious-topic discussions [+M]
- LlamaLo added knowledge in almost every post, mostly correct, and most posts were internally coherent [+M]
- LlamaLo occasionally employed an aggressive or sarcastic tone, sometimes without user provocation, though it changed tone after being commented on [~M]
- LlamaLo's responses to social posts were solely social and it did not push back to resume the discussion [-W]
- LlamaLo exhibited bias and presented contested assertions as facts, notably in the Israeli-Palestinian conflict discussion [-W]
Related Products and Programmes¶
-
Key Sources¶
- 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
Page metadata
| Field | Value |
|---|---|
type |
product |
id |
llamalo |
title |
LlamaLo |
description |
LlamaLo is a dialogue chatbot fine-tuned by Yifat Ben-David Kolikant et al. |
status |
review |
product_kind |
software |
generated |
by process:settle-candidates on 2026-10-18 |
trust |
unverified — no one has confirmed this page's content |
Frontmatter is the page's machine-readable record — see the Schema & Guide.