Beyond the Known: Investigating LLMs Performance on Out-of-Domain Intent Detection
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866916145630543872 |
|---|---|
| author | Wang, Pei He, Keqing Wang, Yejie Song, Xiaoshuai Mou, Yutao Wang, Jingang Xian, Yunsen Cai, Xunliang Xu, Weiran |
| author_facet | Wang, Pei He, Keqing Wang, Yejie Song, Xiaoshuai Mou, Yutao Wang, Jingang Xian, Yunsen Cai, Xunliang Xu, Weiran |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_17256 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Beyond the Known: Investigating LLMs Performance on Out-of-Domain Intent Detection Wang, Pei He, Keqing Wang, Yejie Song, Xiaoshuai Mou, Yutao Wang, Jingang Xian, Yunsen Cai, Xunliang Xu, Weiran Computation and Language 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. |
| title | Beyond the Known: Investigating LLMs Performance on Out-of-Domain Intent Detection |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2402.17256 |