用LLM提升对话系统多轮意图识别的准确率与效率
Balancing Accuracy and Efficiency in Multi-Turn Intent Classification for LLM-Powered Dialog Systems in Production
- 用符号调优简化标签，降低多轮对话任务复杂度
- 通过伪标签生成合成数据，准确率提升5.09%，标注成本降40%
- 适合资源有限的工业级多语言对话系统部署
准确的多轮意图分类对推进对话AI系统至关重要。然而，全面数据集稀缺以及对话轮次间上下文依赖关系复杂等问题制约了进展。本文提出两种基于大语言模型（LLMs）的新方法，以提升生产环境中对话系统的可扩展性并降低延迟。首先引入符号调优（Symbol Tuning），将意图标签简化以降低任务复杂度，提升多轮对话性能；其次提出C-LARA（一致性感知、语言自适应检索增强）框架，利用LLMs进行数据增强与伪标签生成，构建合成多轮对话数据。这些增强数据用于微调一个小型高效模型，适合实际部署。在多语言对话数据集上的实验表明，该方法显著提升分类准确率与资源效率：准确率提高5.09%，标注成本降低40%，并在低资源多语言工业系统中实现可扩展部署，展现出良好的实用价值。
原文摘要 · Abstract (English)
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 dialogue turns hinder progress. This paper presents two novel approaches leveraging Large Language Models (LLMs) to enhance scalability and reduce latency in production dialogue systems. First, we introduce Symbol Tuning, which simplifies intent labels to reduce task complexity and improve performance in multi-turn dialogues. Second, we propose C-LARA (Consistency-aware, Linguistics Adaptive Retrieval Augmentation), a framework that employs LLMs for data augmentation and pseudo-labeling to generate synthetic multi-turn dialogues. These enriched datasets are used to fine-tune a small, efficient model suitable for deployment. Experiments conducted on multilingual dialogue datasets demonstrate significant improvements in classification accuracy and resource efficiency. Our methods enhance multi-turn intent classification accuracy by 5.09%, reduce annotation costs by 40%, and enable scalable deployment in low-resource multilingual industrial systems, highlighting their practicality and impact.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。