Intent Recognition and Out-of-Scope Detection using LLMs in Multi-party Conversations

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Castillo-López, Galo, de Chalendar, Gaël, Semmar, Nasredine
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918107596980224
author Castillo-López, Galo
de Chalendar, Gaël
Semmar, Nasredine
author_facet Castillo-López, Galo
de Chalendar, Gaël
Semmar, Nasredine
contents Intent recognition is a fundamental component in task-oriented dialogue systems (TODS). Determining user intents and detecting whether an intent is Out-of-Scope (OOS) is crucial for TODS to provide reliable responses. However, traditional TODS require large amount of annotated data. In this work we propose a hybrid approach to combine BERT and LLMs in zero and few-shot settings to recognize intents and detect OOS utterances. Our approach leverages LLMs generalization power and BERT's computational efficiency in such scenarios. We evaluate our method on multi-party conversation corpora and observe that sharing information from BERT outputs to LLMs leads to system performance improvement.
format Preprint
id arxiv_https___arxiv_org_abs_2507_22289
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Intent Recognition and Out-of-Scope Detection using LLMs in Multi-party Conversations
Castillo-López, Galo
de Chalendar, Gaël
Semmar, Nasredine
Computation and Language
Machine Learning
Intent recognition is a fundamental component in task-oriented dialogue systems (TODS). Determining user intents and detecting whether an intent is Out-of-Scope (OOS) is crucial for TODS to provide reliable responses. However, traditional TODS require large amount of annotated data. In this work we propose a hybrid approach to combine BERT and LLMs in zero and few-shot settings to recognize intents and detect OOS utterances. Our approach leverages LLMs generalization power and BERT's computational efficiency in such scenarios. We evaluate our method on multi-party conversation corpora and observe that sharing information from BERT outputs to LLMs leads to system performance improvement.
title Intent Recognition and Out-of-Scope Detection using LLMs in Multi-party Conversations
topic Computation and Language
Machine Learning
url https://arxiv.org/abs/2507.22289