Showing cs.HCShow all
2 papers · 1 filter
cs.HC2026
Personality-Aware Reinforcement Learning for Persuasive Dialogue with LLM-Driven Simulation
Donghuo Zeng, Roberto Legaspi, Kazushi Ikeda
Effective persuasive dialogue agents adapt their strategies to individual users, accounting for the evolution of their psychological states and intentions throughout conversations.…
cs.HC2025
Generative Framework for Personalized Persuasion: Inferring Causal, Counterfactual, and Latent Knowledge
Donghuo Zeng, Roberto Legaspi, Yuewen Sun +4
We hypothesize that optimal system responses emerge from adaptive strategies grounded in causal and counterfactual knowledge. Counterfactual inference allows us to create hypotheti…