In a 75-session pilot with two Greek students per session, ChatGPT 4.0 produced consensus proposals with higher average cosine similarity to initial participant opinions and required fewer iterations than Mistral Large 2 or AI21 Jamba.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.HC 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
From Divergence to Consensus: Evaluating the Role of Large Language Models in Facilitating Agreement through Adaptive Strategies
In a 75-session pilot with two Greek students per session, ChatGPT 4.0 produced consensus proposals with higher average cosine similarity to initial participant opinions and required fewer iterations than Mistral Large 2 or AI21 Jamba.