Zero-Shot Prompting for Implicit Intent Prediction and Recommendation with Commonsense Reasoning

TL;DR

This paper introduces a framework enabling virtual assistants to infer implicit user intents using commonsense reasoning and zero-shot prompting, reducing interaction complexity and enhancing multi-domain dialogue capabilities.

Contribution

It presents a novel multi-domain dialogue system that infers implicit intents and leverages zero-shot prompting with large language models for task execution.

Findings

Effective inference of implicit intents demonstrated

Successful zero-shot bot triggering in multi-domain scenarios

Improved interaction efficiency in virtual assistants

Abstract

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.