UPC uses LLM-judge feedback to generate better training dialogues and an easy-to-hard curriculum, improving user-oriented proactivity in open-domain chatbots.
Prompting and evaluating large language models for proactive dialogues: Clarification, target-guided, and non- collaboration
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Enhancing User-Oriented Proactivity in Open-Domain Dialogues with Critic Guidance
UPC uses LLM-judge feedback to generate better training dialogues and an easy-to-hard curriculum, improving user-oriented proactivity in open-domain chatbots.