LARA: Linguistic-Adaptive Retrieval-Augmentation for Multi-Turn Intent Classification
Junhua Liu, Tan Yong Keat, Bin Fu, Kwan Hui Lim
Abstract
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 numerous 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.
BibTeX
@inproceedings{liu-etal-2024-lara,
title = "{LARA}: Linguistic-Adaptive Retrieval-Augmentation for Multi-Turn Intent Classification",
author = "Liu, Junhua and
Keat, Tan Yong and
Fu, Bin and
Lim, Kwan Hui",
editor = "Dernoncourt, Franck and
Preo{\c{t}}iuc-Pietro, Daniel and
Shimorina, Anastasia",
booktitle = "Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing: Industry Track",
month = nov,
year = "2024",
address = "Miami, Florida, US",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.emnlp-industry.82/",
doi = "10.18653/v1/2024.emnlp-industry.82",
pages = "1096--1106"
}