A framework that combines LLM-based user personas, breakdown detection, and dialogue rating to test chatbots, with a non-cooperative simulator that triggers more breakdowns than cooperative baselines.
It seems there was an issue with the reservation time format. For The Pint Shop, could you please specify the time in a format like
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
-
ChatChecker: A Framework for Dialogue System Testing and Evaluation Through Non-cooperative User Simulation
A framework that combines LLM-based user personas, breakdown detection, and dialogue rating to test chatbots, with a non-cooperative simulator that triggers more breakdowns than cooperative baselines.