Bridging Reasoning and Action: Hybrid LLM-RL Framework for Efficient Cross-Domain Task-Oriented Dialogue

Documenti analoghi

• Improving Multi-Domain Task-Oriented Dialogue System with Offline Reinforcement Learning
  di: Prajapat, Dharmendra, et al.
  Pubblicazione: (2024)
• HyperSumm-RL: A Dialogue Summarization Framework for Modeling Leadership Perception in Social Robots
  di: Das, Subasish
  Pubblicazione: (2025)
• Learning from Implicit User Feedback, Emotions and Demographic Information in Task-Oriented and Document-Grounded Dialogues
  di: Petrak, Dominic, et al.
  Pubblicazione: (2024)
• Exploring ReAct Prompting for Task-Oriented Dialogue: Insights and Shortcomings
  di: Elizabeth, Michelle, et al.
  Pubblicazione: (2024)
• Context Does Matter: Implications for Crowdsourced Evaluation Labels in Task-Oriented Dialogue Systems
  di: Siro, Clemencia, et al.
  Pubblicazione: (2024)