Users describe a conversation flow as a JSON graph and two LLM agents generate the full task-oriented dialogue from it.
Hello, it’s GPT-2 - how can I help you? towards the use of pretrained language models for task-oriented dialogue systems
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
support 1representative citing papers
citing papers explorer
-
Leveraging Graph Structures and Large Language Models for End-to-End Synthetic Task-Oriented Dialogues
Users describe a conversation flow as a JSON graph and two LLM agents generate the full task-oriented dialogue from it.