Zero-Shot Prompting for Implicit Intent Prediction and Recommendation with Commonsense Reasoning
This addresses the inefficiency of multi-domain dialogue systems for users by reducing complex interactions, though it appears incremental as it builds on existing language models and commonsense reasoning techniques.
The paper tackles the problem of virtual assistants requiring explicit user intents by proposing a framework that infers implicit intents from user utterances using commonsense reasoning and zero-shot prompting with a large language model, demonstrating effectiveness in predicting intents and recommending bots without task-specific training.
Intelligent virtual assistants are currently designed to perform tasks or services explicitly mentioned by users, so multiple related domains or tasks need to be performed one by one through a long conversation with many explicit intents. Instead, human assistants are capable of reasoning (multiple) implicit intents based on user utterances via commonsense knowledge, reducing complex interactions and improving practicality. Therefore, this paper proposes a framework of multi-domain dialogue systems, which can automatically infer implicit intents based on user utterances and then perform zero-shot prompting using a large pre-trained language model to trigger suitable single task-oriented bots. The proposed framework is demonstrated effective to realize implicit intents and recommend associated bots in a zero-shot manner.