This study marks a significant advancement by harnessing Large Language Models (LLMs) for multi-intent spoken language understanding (SLU), proposing a unique methodology that capitalizes on the generative power of LLMs within an SLU context. Our innovative technique reconfigures entity slots specifically for LLM application in multi-intent SLU environments and introduces the concept of Sub-Intent Instruction (SII), enhancing the dissection and interpretation of intricate, multi-intent communication within varied domains. The resultant datasets, dubbed LM-MixATIS and LM-MixSNIPS, are crafted from pre-existing benchmarks. Our research illustrates that LLMs can match and potentially excel beyond the capabilities of current state-of-the-art multi-intent SLU models. It further explores LLM efficacy across various intent configurations and dataset proportions. Moreover, we introduce two pioneering metrics, Entity Slot Accuracy (ESA) and Combined Semantic Accuracy (CSA), to provide an in-depth analysis of LLM proficiency in this complex field.

本研究通过利用大型语言模型（LLMs）进行多意图口语语言理解（SLU）的研究，提出一种独特的方法，充分利用LLMs的生成能力，在SLU环境中重构了实体槽位，引入了子意图指令（SII）的概念，增强了对复杂多意图通信的解析和解释，从而形成了名为LM-MixATIS和LM-MixSNIPS的结果数据集。我们的研究表明，LLMs可以匹配并潜在地超越当前最先进的多意图SLU模型的能力。此外，我们还介绍了两个开创性的度量标准，实体槽位准确度（ESA）和综合语义准确度（CSA），以深入分析LLMs在这一复杂领域的熟练程度。

大型语言模型是否理解多意图口语？