Do Vision and Language Models Share Concepts? A Vector Space Alignment Study

Jiaang Li

doi:10.1162/tacl_a_00698

Do Vision and Language Models Share Concepts? A Vector Space Alignment Study

2024-09-30

1

OA

AI

J

Jiaang Li *

Y

Yova Kementchedjhieva

DOI：10.1162/tacl_a_00698

Original

Original request for help

Save

Abstract

En 中文

Large-scale pretrained language models (LMs) are said to lack the ability to connect utterances to the world (Bender and Koller, 2020), because they do not have mental models of the world (Mitchell and Krakauer, 2023). If so, one would expect LM representations to be unrelated to representations induced by vision models. We present an empirical evaluation across four families of LMs (BERT, GPT-2, OPT, and LLaMA-2) and three vision model architectures (ResNet, SegFormer, and MAE). Our experiments show that LMs partially converge towards representations isomorphic to those of vision models, subject to dispersion, polysemy, and frequency. This has important implications for both multi-modal processing and the LM understanding debate (Mitchell and Krakauer, 2023).1

Do Vision and Language Models Share Concepts? A Vector Space Alignment Study

Abstract

Journal

Organization