TWIZ-v2: The Wizard of Multimodal Conversational-Stimulus

TL;DR

TWIZ-v2 is a multimodal conversational assistant designed to guide users through complex tasks using voice, images, and videos, with innovations in zero-shot flows and a specialized large language model.

Contribution

The paper introduces TWIZ-v2, a novel multimodal conversational system with robust zero-shot capabilities and a specialized LLM for complex manual task assistance.

Findings

Effective guidance through complex tasks

Supports multimodal stimuli including voice, images, and videos

Robust performance in unseen scenarios

Abstract

In this report, we describe the vision, challenges, and scientific contributions of the Task Wizard team, TWIZ, in the Alexa Prize TaskBot Challenge 2022. Our vision, is to build TWIZ bot as an helpful, multimodal, knowledgeable, and engaging assistant that can guide users towards the successful completion of complex manual tasks. To achieve this, we focus our efforts on three main research questions: (1) Humanly-Shaped Conversations, by providing information in a knowledgeable way; (2) Multimodal Stimulus, making use of various modalities including voice, images, and videos; and (3) Zero-shot Conversational Flows, to improve the robustness of the interaction to unseen scenarios. TWIZ is an assistant capable of supporting a wide range of tasks, with several innovative features such as creative cooking, video navigation through voice, and the robust TWIZ-LLM, a Large Language Model trained for dialoguing about complex manual tasks. Given ratings and feedback provided by users, we observed that TWIZ bot is an effective and robust system, capable of guiding users through tasks while providing several multimodal stimuli.