Large Language Models as Zero-shot Dialogue State Tracker through Function Calling

arXiv:2402.10466v1 Announce Type: new
Abstract: Large language models (LLMs) are increasingly prevalent in conversational systems due to their advanced understanding and generative capabilities in general contexts. However, their effectiveness in task-oriented dialogues (TOD), which requires not only response generation but also effective dialogue state tracking (DST) within specific tasks and domains, remains less satisfying. In this work, we propose a novel approach FnCTOD for solving DST with LLMs through function calling. This method improves zero-shot DST, allowing adaptation to diverse …

abstract advanced arxiv capabilities conversational cs.ai cs.cl dialogue function general generative language language models large language large language models llms specific tasks state systems tasks through tracking type understanding zero-shot