Adding a reflection-and-correction stage trained with ChatGPT-annotated consistency feedback improves response consistency and goal success in goal-oriented proactive dialogue systems across multiple models and datasets.
Title resolution pending
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
-
Enhancing Goal-oriented Proactive Dialogue Systems via Consistency Reflection and Correction
Adding a reflection-and-correction stage trained with ChatGPT-annotated consistency feedback improves response consistency and goal success in goal-oriented proactive dialogue systems across multiple models and datasets.