LARA: Linguistic-Adaptive Retrieval-Augmentation for Multi-Turn Intent Classification

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Liu, Junhua, Tan, Yong Keat, Fu, Bin, Lim, Kwan Hui
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909347169173504
author Liu, Junhua
Tan, Yong Keat
Fu, Bin
Lim, Kwan Hui
author_facet Liu, Junhua
Tan, Yong Keat
Fu, Bin
Lim, Kwan Hui
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2403_16504
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle LARA: Linguistic-Adaptive Retrieval-Augmentation for Multi-Turn Intent Classification
Liu, Junhua
Tan, Yong Keat
Fu, Bin
Lim, Kwan Hui
Computation and Language
Information Retrieval
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.
title LARA: Linguistic-Adaptive Retrieval-Augmentation for Multi-Turn Intent Classification
topic Computation and Language
Information Retrieval
url https://arxiv.org/abs/2403.16504