Saved in:
Bibliographic Details
Main Authors: Bohus, Dan, Andrist, Sean, Bao, Yuwei, Horvitz, Eric, Paradiso, Ann
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2409.10525
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910606592835584
author Bohus, Dan
Andrist, Sean
Bao, Yuwei
Horvitz, Eric
Paradiso, Ann
author_facet Bohus, Dan
Andrist, Sean
Bao, Yuwei
Horvitz, Eric
Paradiso, Ann
contents We report initial work towards constructing ecologically valid benchmarks to assess the capabilities of large multimodal models for engaging in situated collaboration. In contrast to existing benchmarks, in which question-answer pairs are generated post hoc over preexisting or synthetic datasets via templates, human annotators, or large language models (LLMs), we propose and investigate an interactive system-driven approach, where the questions are generated by users in context, during their interactions with an end-to-end situated AI system. We illustrate how the questions that arise are different in form and content from questions typically found in existing embodied question answering (EQA) benchmarks and discuss new real-world challenge problems brought to the fore.
format Preprint
id arxiv_https___arxiv_org_abs_2409_10525
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle "Is This It?": Towards Ecologically Valid Benchmarks for Situated Collaboration
Bohus, Dan
Andrist, Sean
Bao, Yuwei
Horvitz, Eric
Paradiso, Ann
Multimedia
Artificial Intelligence
Computation and Language
We report initial work towards constructing ecologically valid benchmarks to assess the capabilities of large multimodal models for engaging in situated collaboration. In contrast to existing benchmarks, in which question-answer pairs are generated post hoc over preexisting or synthetic datasets via templates, human annotators, or large language models (LLMs), we propose and investigate an interactive system-driven approach, where the questions are generated by users in context, during their interactions with an end-to-end situated AI system. We illustrate how the questions that arise are different in form and content from questions typically found in existing embodied question answering (EQA) benchmarks and discuss new real-world challenge problems brought to the fore.
title "Is This It?": Towards Ecologically Valid Benchmarks for Situated Collaboration
topic Multimedia
Artificial Intelligence
Computation and Language
url https://arxiv.org/abs/2409.10525