Beyond the Known: Investigating LLMs Performance on Out-of-Domain Intent Detection
This addresses the problem of improving intent detection in dialogue systems for developers, but it is incremental as it evaluates existing LLMs without proposing a new method.
The paper investigates the performance of large language models (LLMs) on out-of-domain intent detection for task-oriented dialogue systems, finding that LLMs show strong zero-shot and few-shot capabilities but are still at a disadvantage compared to fine-tuned models.
Out-of-domain (OOD) intent detection aims to examine whether the user's query falls outside the predefined domain of the system, which is crucial for the proper functioning of task-oriented dialogue (TOD) systems. Previous methods address it by fine-tuning discriminative models. Recently, some studies have been exploring the application of large language models (LLMs) represented by ChatGPT to various downstream tasks, but it is still unclear for their ability on OOD detection task.This paper conducts a comprehensive evaluation of LLMs under various experimental settings, and then outline the strengths and weaknesses of LLMs. We find that LLMs exhibit strong zero-shot and few-shot capabilities, but is still at a disadvantage compared to models fine-tuned with full resource. More deeply, through a series of additional analysis experiments, we discuss and summarize the challenges faced by LLMs and provide guidance for future work including injecting domain knowledge, strengthening knowledge transfer from IND(In-domain) to OOD, and understanding long instructions.