A reinforcement learning loop with a simulated engagement model trains an LLM to generate posts whose sentiment adapts to a network's opinion distribution, boosting simulated engagement on synthetic and real political networks.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Engagement-Driven Content Generation with Large Language Models
A reinforcement learning loop with a simulated engagement model trains an LLM to generate posts whose sentiment adapts to a network's opinion distribution, boosting simulated engagement on synthetic and real political networks.