AmbiK: Dataset of Ambiguous Tasks in Kitchen Environment

TL;DR

AmbiK is a comprehensive, human-validated textual dataset of 1000 ambiguous and unambiguous kitchen tasks designed to facilitate the comparison of ambiguity detection methods for embodied agents.

Contribution

We introduce AmbiK, a novel, fully textual dataset of ambiguous kitchen tasks with detailed annotations, enabling standardized evaluation of ambiguity detection techniques.

Findings

Dataset includes 2000 tasks with ambiguity categories

Contains environment descriptions, questions, answers, and task plans

Facilitates unified benchmarking of ambiguity detection methods

Abstract

As a part of an embodied agent, Large Language Models (LLMs) are typically used for behavior planning given natural language instructions from the user. However, dealing with ambiguous instructions in real-world environments remains a challenge for LLMs. Various methods for task ambiguity detection have been proposed. However, it is difficult to compare them because they are tested on different datasets and there is no universal benchmark. For this reason, we propose AmbiK (Ambiguous Tasks in Kitchen Environment), the fully textual dataset of ambiguous instructions addressed to a robot in a kitchen environment. AmbiK was collected with the assistance of LLMs and is human-validated. It comprises 1000 pairs of ambiguous tasks and their unambiguous counterparts, categorized by ambiguity type (Human Preferences, Common Sense Knowledge, Safety), with environment descriptions, clarifying questions and answers, user intents, and task plans, for a total of 2000 tasks. We hope that AmbiK will enable researchers to perform a unified comparison of ambiguity detection methods. AmbiK is available at https://github.com/cog-model/AmbiK-dataset.