Search Results for author:
Found 3 papers, 1 papers with code
BETOLD: A Task-Oriented Dialog Dataset for Breakdown Detection
Ideally TOD systems should be able to detect dialog breakdowns to prevent users from quitting a conversation and to encourage them to interact with the system again.
Reliable LLM-based User Simulator for Task-Oriented Dialogue Systems
Notably, we have observed that fine-tuning enhances the simulator's coherence with user goals, effectively mitigating hallucinations -- a major source of inconsistencies in simulator responses.
In-Context Learning User Simulators for Task-Oriented Dialog Systems
This paper presents a novel application of large language models in user simulation for task-oriented dialog systems, specifically focusing on an in-context learning approach.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
