Task-oriented Dialogue Systems (TODS) often face the challenge of encountering new intents. New Intent Discovery (NID) is a crucial task that aims to identify these novel intents while maintaining the capability to recognize existing ones. Previous efforts to adapt TODS to new intents have struggled with inadequate semantic representation or have depended on external knowledge, which is often not scalable or flexible. Recently, Large Language Models (LLMs) have demonstrated strong zero-shot capabilities; however, their scale can be impractical for real-world applications that involve extensive queries. To address the limitations of existing NID methods by leveraging LLMs, we propose LANID, a framework that enhances the semantic representation of lightweight NID encoders with the guidance of LLMs. Specifically, LANID employs the $K$-nearest neighbors and Density-Based Spatial Clustering of Applications with Noise (DBSCAN) algorithms to sample selective utterance pairs from the training set. It then queries an LLM to ascertain the relationships between these pairs. The data produced from this process is utilized to design a contrastive fine-tuning task, which is then used to train a small encoder with a contrastive triplet loss. Our experimental results demonstrate the efficacy of the proposed method across three distinct NID datasets, surpassing strong baselines in both unsupervised and semi-supervised settings. Our code is available at https://github.com/floatSDSDS/LANID.

翻译：面向任务的对话系统（TODS）常常面临遇到新意图的挑战。新意图发现（NID）是一项关键任务，其目标是在保持识别现有意图能力的同时，识别这些新颖意图。以往使TODS适应新意图的努力，要么受限于语义表示不足，要么依赖于通常不可扩展或不够灵活的外部知识。最近，大语言模型（LLMs）展现了强大的零样本能力；然而，其规模对于涉及大量查询的实际应用而言可能不切实际。为了利用LLMs克服现有NID方法的局限性，我们提出了LANID框架，该框架在LLMs的指导下增强轻量级NID编码器的语义表示。具体而言，LANID采用$K$近邻和基于密度的噪声应用空间聚类（DBSCAN）算法，从训练集中采样选择性的话语对。随后，它查询一个LLM以确定这些话语对之间的关系。此过程产生的数据被用于设计一个对比微调任务，进而用于通过对比三元组损失训练一个小型编码器。我们的实验结果证明了所提方法在三个不同的NID数据集上的有效性，在无监督和半监督设置下均超越了强基线。我们的代码可在 https://github.com/floatSDSDS/LANID 获取。