"Mango Mango, How to Let The Lettuce Dry Without A Spinner?": Exploring User Perceptions of Using An LLM-Based Conversational Assistant Toward Cooking Partner

TL;DR

This study explores user perceptions of an LLM-based conversational assistant in cooking, revealing its strengths in customization and information provision, while highlighting the need for greater adaptability and engagement.

Contribution

It provides insights into user experiences with an LLM-based cooking assistant and proposes five design considerations for enhancing future conversational AI systems.

Findings

Users value customization and extensive information

Users want more adaptive and suggestive responses

Users treat the system as a personal partner

Abstract

The rapid advancement of Large Language Models (LLMs) has created numerous potentials for integration with conversational assistants (CAs) assisting people in their daily tasks, particularly due to their extensive flexibility. However, users' real-world experiences interacting with these assistants remain unexplored. In this research, we chose cooking, a complex daily task, as a scenario to explore people's successful and unsatisfactory experiences while receiving assistance from an LLM-based CA, Mango Mango. We discovered that participants value the system's ability to offer customized instructions based on context, provide extensive information beyond the recipe, and assist them in dynamic task planning. However, users expect the system to be more adaptive to oral conversation and provide more suggestive responses to keep them actively involved. Recognizing that users began treating our LLM-CA as a personal assistant or even a partner rather than just a recipe-reading tool, we propose five design considerations for future development.