Modified classical opinion dynamics models with a bias term capture LLM network opinion evolution better than naive averaging, reducing mean opinion error by up to 88% and generalizing across models, topics, and networks.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.MA 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Characterizing Opinion Evolution of Networked LLMs
Modified classical opinion dynamics models with a bias term capture LLM network opinion evolution better than naive averaging, reducing mean opinion error by up to 88% and generalizing across models, topics, and networks.