ViCor: Bridging Visual Understanding and Commonsense Reasoning with Large Language Models

Kaiwen Zhou, Kwonjoon Lee, Teruhisa Misu, Xin Wang

Abstract
In our work, we explore the synergistic capabilities of pre-trained vision-and-language models (VLMs) and large language models (LLMs) on visual commonsense reasoning (VCR) problems. We find that VLMs and LLMs-based decision pipelines are good at different kinds of VCR problems. Pre-trained VLMs exhibit strong performance for problems involving understanding the literal visual content, which we noted as visual commonsense understanding (VCU). For problems where the goal is to infer conclusions beyond image content, which we noted as visual commonsense inference (VCI), VLMs face difficulties, while LLMs, given sufficient visual evidence, can use commonsense to infer the answer well. We empirically validate this by letting LLMs classify VCR problems into these two categories and show the significant difference between VLM and LLM with image caption decision pipelines on two subproblems. Moreover, we identify a challenge with VLMs’ passive perception, which may miss crucial context information, leading to incorrect reasoning by LLMs. Based on these, we suggest a collaborative approach, named ViCor, where pre-trained LLMs serve as problem classifiers to analyze the problem category, then either use VLMs to answer the question directly or actively instruct VLMs to concentrate on and gather relevant visual elements to support potential commonsense inferences. We evaluate our framework on two VCR benchmark datasets and outperform all other methods without in-domain fine-tuning.
Anthology ID:
2024.findings-acl.640
Volume:
Findings of the Association for Computational Linguistics: ACL 2024
Month:
August
Year:
2024
Address:
Bangkok, Thailand
Editors:
Lun-Wei Ku, Andre Martins, Vivek Srikumar
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
10783–10795
Language:
URL:
https://aclanthology.org/2024.findings-acl.640
DOI:
10.18653/v1/2024.findings-acl.640
Bibkey:
Cite (ACL):
Kaiwen Zhou, Kwonjoon Lee, Teruhisa Misu, and Xin Wang. 2024. ViCor: Bridging Visual Understanding and Commonsense Reasoning with Large Language Models. In Findings of the Association for Computational Linguistics: ACL 2024, pages 10783–10795, Bangkok, Thailand. Association for Computational Linguistics.
Cite (Informal):
ViCor: Bridging Visual Understanding and Commonsense Reasoning with Large Language Models (Zhou et al., Findings 2024)
Copy Citation:
PDF:
https://preview.aclanthology.org/autopr/2024.findings-acl.640.pdf
PDF Search Fix metadata