Intent Recognition and Out-of-Scope Detection using LLMs in Multi-party Conversations
This work addresses the problem of reducing annotation needs for task-oriented dialogue systems, but it appears incremental as it builds on existing methods like BERT and LLMs.
The paper tackled intent recognition and out-of-scope detection in multi-party conversations by proposing a hybrid approach combining BERT and LLMs in zero and few-shot settings, resulting in system performance improvement as observed on conversation corpora.
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.