Following the significant achievements of large language models (LLMs), researchers have employed in-context learning for text classification tasks. However, these studies focused on monolingual, single-turn classification tasks. In this paper, we introduce LARA (Linguistic-Adaptive Retrieval-Augmented Language Models), designed to enhance accuracy in multi-turn classification tasks across six languages, accommodating numerous intents in chatbot interactions. Multi-turn intent classification is notably challenging due to the complexity and evolving nature of conversational contexts. LARA tackles these issues by combining a fine-tuned smaller model with a retrieval-augmented mechanism, integrated within the architecture of LLMs. This integration allows LARA to dynamically utilize past dialogues and relevant intents, thereby improving the understanding of the context. Furthermore, our adaptive retrieval techniques bolster the cross-lingual capabilities of LLMs without extensive retraining and fine-tune. Comprehensive experiments demonstrate that LARA achieves state-of-the-art performance on multi-turn intent classification tasks, enhancing the average accuracy by 3.67% compared to existing methods.

翻译：继大语言模型取得重大突破之后，研究者们采用上下文学习技术处理文本分类任务。然而，现有研究主要聚焦于单语言、单轮分类任务。本文提出LARA（语言自适应检索增强语言模型），旨在提升跨六种语言的多轮分类任务精度，以应对聊天机器人交互中普遍存在的多意图场景。多轮意图分类因对话语境的复杂性与动态演化特性而极具挑战性。LARA通过将经过微调的轻量级模型与检索增强机制深度融合至大语言模型架构中，实现对该问题的有效应对：该模型既可动态利用历史对话与相关意图增强上下文理解，其自适应检索技术还能在不需大规模重新训练与微调的前提下强化大语言模型的跨语言能力。全面实验表明，LARA在多轮意图分类任务上达到最优性能，相较现有方法平均准确率提升3.67%。