The tasks of out-of-domain (OOD) intent discovery and generalized intent
discovery (GID) aim to extend a closed intent classifier to open-world intent
sets, which is crucial to task-oriented dialogue (TOD) systems. Previous
methods address them by fine-tuning discriminative models. Recently, although
some studies have been exploring the application of large language models
(LLMs) represented by ChatGPT to various downstream tasks, it is still unclear
for the ability of ChatGPT to discover and incrementally extent OOD intents. In
this paper, we comprehensively evaluate ChatGPT on OOD intent discovery and
GID, and then outline the strengths and weaknesses of ChatGPT. Overall, ChatGPT
exhibits consistent advantages under zero-shot settings, but is still at a
disadvantage compared to fine-tuned models. More deeply, through a series of
analytical experiments, we summarize and discuss the challenges faced by LLMs
including clustering, domain-specific understanding, and cross-domain
in-context learning scenarios. Finally, we provide empirical guidance for
future directions to address these challenges.

ChatGPT 对 OOD 意图探索和广义意图探索进行了全面评估，并概述了 ChatGPT 的优势和劣势。ChatGPT 在零样本设置下展现了一致的优势，但与微调模型相比仍处于劣势。通过一系列分析实验，我们总结和讨论了 LLM 面临的挑战，包括聚类、领域特定理解和跨领域情境学习场景。最后，我们提供了未来解决这些挑战的经验指导。

大型语言模型应用于开放领域意图发现和识别的评估：ChatGPT

Large Language Models Meet Open-World Intent Discovery and Recognition:  An Evaluation of ChatGPT

In a practical dialogue system, users may input out-of-domain (OOD) queries.
The Generalized Intent Discovery (GID) task aims to discover OOD intents from
OOD queries and extend them to the in-domain (IND) classifier. However, GID
only considers one stage of OOD learning, and needs to utilize the data in all
previous stages for joint training, which limits its wide application in
reality. In this paper, we introduce a new task, Continual Generalized Intent
Discovery (CGID), which aims to continuously and automatically discover OOD
intents from dynamic OOD data streams and then incrementally add them to the
classifier with almost no previous data, thus moving towards dynamic intent
recognition in an open world. Next, we propose a method called Prototype-guided
Learning with Replay and Distillation (PLRD) for CGID, which bootstraps new
intent discovery through class prototypes and balances new and old intents
through data replay and feature distillation. Finally, we conduct detailed
experiments and analysis to verify the effectiveness of PLRD and understand the
key challenges of CGID for future research.

通过原型引导的学习与重放和蒸馏方法，我们提出了一种连续的广义意图发现任务，旨在不断自动地从动态 OOD 数据流中发现 OOD 意图，并几乎不需要先前的数据将它们逐步添加到分类器中，从而朝着开放世界的动态意图识别迈进。

持续化的通用意图发现：迈向动态和开放式意图识别

Continual Generalized Intent Discovery: Marching Towards Dynamic and  Open-world Intent Recognition

Traditional intent classification models are based on a pre-defined intent
set and only recognize limited in-domain (IND) intent classes. But users may
input out-of-domain (OOD) queries in a practical dialogue system. Such OOD
queries can provide directions for future improvement. In this paper, we define
a new task, Generalized Intent Discovery (GID), which aims to extend an IND
intent classifier to an open-world intent set including IND and OOD intents. We
hope to simultaneously classify a set of labeled IND intent classes while
discovering and recognizing new unlabeled OOD types incrementally. We construct
three public datasets for different application scenarios and propose two kinds
of frameworks, pipeline-based and end-to-end for future work. Further, we
conduct exhaustive experiments and qualitative analysis to comprehend key
challenges and provide new guidance for future GID research.

提出了一种新的任务 —— 广义意图发现（GID），旨在将传统的领域内意图分类器扩展到包括领域外意图在内的开放世界意图集。为未来的工作提出了基于管道和端对端两种框架，并构建了三个不同应用场景的公共数据集，通过详尽实验和定性分析，为未来 GID 研究提供了新的指导。