Task-Oriented Dialogue with In-Context Learning

arXiv:2402.12234v1 Announce Type: new
Abstract: We describe a system for building task-oriented dialogue systems combining the in-context learning abilities of large language models (LLMs) with the deterministic execution of business logic. LLMs are used to translate between the surface form of the conversation and a domain-specific language (DSL) which is used to progress the business logic. We compare our approach to the intent-based NLU approach predominantly used in industry today. Our experiments show that developing chatbots with our system requires …

abstract arxiv building business business logic context conversation cs.cl dialogue domain form in-context learning language language models large language large language models llms logic progress surface systems the conversation translate type