LARA: Linguistic-Adaptive Retrieval-Augmentation for Multi-Turn Intent Classification
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.
Code (0)
등록된 구현이 없습니다.
Tasks
ChatbotClassificationIn-Context Learningintent-classificationIntent ClassificationRetrievaltext-classificationText ClassificationSimilar Papers 제목 키워드 기반
Balancing Accuracy and Efficiency in Multi-Turn Intent Classification for LLM-Powered Dialog Systems in Production
Accurate multi-turn intent classification is essential for advancing conversational AI systems. However, challenges such as the scarcity of comprehensive datasets and the complexity of contextual dependencies across dial…
ClassificationData Augmentationintent-classificationIntent ClassificationCLaRa: Bridging Retrieval and Generation with Continuous Latent Reasoning
Retrieval-augmented generation (RAG) enhances large language models (LLMs) with external knowledge but still suffers from long contexts and disjoint retrieval-generation optimization. In this work, we propose CLaRa (Cont…
Question AnsweringCredo: Declarative Control of LLM Pipelines via Beliefs and Policies
Agentic AI systems are becoming commonplace in domains that require long-lived, stateful decision-making in continuously evolving conditions. As such, correctness depends not only on the output of individual model calls,…
Boosting the Capabilities of Compact Models in Low-Data Contexts with Large Language Models and Retrieval-Augmented Generation
The data and compute requirements of current language modeling technology pose challenges for the processing and analysis of low-resource languages. Declarative linguistic knowledge has the potential to partially bridge …
DescriptiveInductive BiasLanguage ModelingLanguage Modelling+5Optimizing LLM Prompt Engineering with DSPy Based Declarative Learning
Large Language Models (LLMs) have shown strong performance across a wide range of natural language processing tasks; however, their effectiveness is highly dependent on prompt design, structure, and embedded reasoning si…
Prompt Engineering