DialogXpert combines a frozen LLM action proposer with a lightweight online Q-network and emotion tracking, achieving sub-3-turn dialogue success rates above 94 percent in LLM-simulated benchmarks.
Your responses are auto-saved after each item
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
DialogXpert: Driving Intelligent and Emotion-Aware Conversations through Online Value-Based Reinforcement Learning with LLM Priors
DialogXpert combines a frozen LLM action proposer with a lightweight online Q-network and emotion tracking, achieving sub-3-turn dialogue success rates above 94 percent in LLM-simulated benchmarks.