Large Language Models as Zero-shot Dialogue State Tracker through Function Calling
CoRR(2024)
摘要
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 domains without extensive data collection or
model tuning. Our experimental results demonstrate that our approach achieves
exceptional performance with both modestly sized open-source and also
proprietary LLMs: with in-context prompting it enables various 7B or 13B
parameter models to surpass the previous state-of-the-art (SOTA) achieved by
ChatGPT, and improves ChatGPT's performance beating the SOTA by 5.6
Individual model results for GPT-3.5 and GPT-4 are boosted by 4.8
respectively. We also show that by fine-tuning on a small collection of diverse
task-oriented dialogues, we can equip modestly sized models, specifically a 13B
parameter LLaMA2-Chat model, with function-calling capabilities and DST
performance comparable to ChatGPT while maintaining their chat capabilities. We
plan to open-source experimental code and model.
更多查看译文
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要