用少量标注数据训练高效任务型对话系统
Spec-TOD: A Specialized Instruction-Tuned LLM Framework for Efficient Task-Oriented Dialogue Systems
- 通过显式任务指令微调大模型，构建专用对话框架
- 仅需少量标注数据即可达到可比性能
- 适合资源受限场景下的对话系统开发
任务型对话（TOD）系统支持用户与机器的目标驱动交互。尽管深度学习取得进展，但现有系统在标注数据有限的低资源场景下表现不佳。为此，我们提出Spec-TOD，一种新型端到端TOD框架，可在少量数据下训练高效对话系统。该框架引入两项创新：(i) 基于显式任务指令的专用端到端TOD架构，适配指令微调的大语言模型（LLM）；(ii) 采用轻量级、专用化LLM的高效训练策略，在极少监督条件下实现强性能。在广泛使用的MultiWOZ数据集上的实验表明，Spec-TOD在显著减少标注数据需求的同时，仍保持竞争力。结果证明该框架在低资源环境下推进高效可靠对话系统的潜力。
原文摘要 · Abstract (English)
Task-oriented dialogue (TOD) systems facilitate goal-driven interactions between users and machines. While recent advances in deep learning have improved the performance, TOD systems often struggle in low-resource scenarios with limited labeled data. To address this challenge, we propose Spec-TOD, a novel framework designed to train an end-to-end TOD system with limited data. Spec-TOD introduces two main innovations: (i) a novel specialized end-to-end TOD framework that incorporates explicit task instructions for instruction-tuned large language models (LLMs), and (ii) an efficient training strategy that leverages lightweight, specialized LLMs to achieve strong performance with minimal supervision. Experiments on the MultiWOZ dataset, a widely used TOD benchmark, demonstrate that Spec-TOD achieves competitive results while significantly reducing the need for labeled data. These findings highlight the potential of the proposed framework in advancing efficient and effective TOD systems in low-resource settings.
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。