LARA: Linguistic-Adaptive Retrieval-Augmentation for Multi-Turn Intent Classification
This work addresses the problem of accurately classifying intents in multi-turn conversations for chatbot interactions across multiple languages, representing an incremental advancement in the field.
The paper tackles the challenge of multi-turn intent classification in conversational contexts by introducing LARA, a framework that combines a fine-tuned model with retrieval-augmentation, achieving state-of-the-art performance with an average accuracy improvement of 3.67% over existing methods.
Multi-turn intent classification is notably challenging due to the complexity and evolving nature of conversational contexts. This paper introduces LARA, a Linguistic-Adaptive Retrieval-Augmentation framework to enhance accuracy in multi-turn classification tasks across six languages, accommodating a large number of intents in chatbot interactions. LARA combines a fine-tuned smaller model with a retrieval-augmented mechanism, integrated within the architecture of LLMs. The 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-tuning. Comprehensive experiments demonstrate that LARA achieves state-of-the-art performance on multi-turn intent classification tasks, enhancing the average accuracy by 3.67\% from state-of-the-art single-turn intent classifiers.