Saved in:
Bibliographic Details
Main Authors: Ivanova, Anastasiia, Bakaeva, Eva, Volovikova, Zoya, Kovalev, Alexey K., Panov, Aleksandr I.
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2506.04089
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916778825744384
author Ivanova, Anastasiia
Bakaeva, Eva
Volovikova, Zoya
Kovalev, Alexey K.
Panov, Aleksandr I.
author_facet Ivanova, Anastasiia
Bakaeva, Eva
Volovikova, Zoya
Kovalev, Alexey K.
Panov, Aleksandr I.
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2506_04089
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle AmbiK: Dataset of Ambiguous Tasks in Kitchen Environment
Ivanova, Anastasiia
Bakaeva, Eva
Volovikova, Zoya
Kovalev, Alexey K.
Panov, Aleksandr I.
Machine Learning
Artificial Intelligence
Computation and Language
Robotics
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.
title AmbiK: Dataset of Ambiguous Tasks in Kitchen Environment
topic Machine Learning
Artificial Intelligence
Computation and Language
Robotics
url https://arxiv.org/abs/2506.04089