The DOI matches its Crossref record; 73 of the 73 references it cites were found in a registry or an index.
Do Vision and Language Models Share Concepts? A Vector Space Alignment Study
Open accessAbstract
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
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“Also, Li et al. [111] demonstrate that language models partially converge towards representations isomorphic to those of vision models.”
From Understanding World or Predicting Future? A Comprehensive Survey of World Models (2026) · cites this paper as [111]
Citations
Cites
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474 · cited 1×
“We dial back from function and study whether the concept representations converge toward structural similarity (isomorphism).”
BackgroundBERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2019) · Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers) · doi:10.18653/v1/n19-1423 · Cited by 54,325 · cited 1×
“More related to our work, Huh et al. (2024) proposes a similar hypothesis, although studying it from a different perspective, and our findings corroborate theirs.”
ResultImageNet Large Scale Visual Recognition Challenge
Russakovsky, O., Deng, J., Su, H., Krause, J., Satheesh, S., Ma, S., Huang, Z., Karpathy, A., Khosla, A., Bernstein, M., et al. (2015) · International Journal of Computer Vision · doi:10.1007/s11263-015-0816-y · Cited by 39,380 · cited 4×
“We build bimodal dictionaries of image-text pairs based on the ImageNet-21K dataset (Russakovsky et al., 2015) and the CLDI (cross-lingual dictionary induction) dataset (Hartmann and Søgaard, 2018).”
MethodInfluentialPyTorch: An Imperative Style, High-Performance Deep Learning Library
Paszke, A., Gross, S., Massa, F., Lerer, A., Bradbury, J., Chanan, G., Killeen, T., Lin, Z., Gimelshein, N., Antiga, L., et al. (2019) · arXiv · doi:10.48550/arxiv.1912.01703 · Cited by 31,473
Advances in Neural Information Processing Systems 19
(2007) · The MIT Press eBooks · doi:10.52202/085713 · Cited by 15,539
Learning Transferable Visual Models From Natural Language Supervision
Radford, A., Kim, J. W., Hallacy, C., Ramesh, A., Goh, G., Agarwal, S., Sastry, G., Askell, A., Mishkin, P., Clark, J., et al. (2021) · arXiv · doi:10.48550/arxiv.2103.00020 · Cited by 15,293 · cited 7×
“CLIP Results.”
MethodInfluentialTransformers: State-of-the-Art Natural Language Processing
Wolf, T., Debut, L., Sanh, V., Chaumond, J., Delangue, C., Moi, A., Cistac, P., Rault, T., Louf, R., Funtowicz, M., et al. (2020) · Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: System Demonstrations · doi:10.18653/v1/2020.emnlp-demos.6 · Cited by 8,741
Masked Autoencoders Are Scalable Vision Learners
He, K., Chen, X., Xie, S., Li, Y., Dollar, P., & Girshick, R. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52688.2022.01553 · Cited by 8,489 · cited 1×
“We dial back from function and study whether the concept representations converge toward structural similarity (isomorphism).”
BackgroundSearle, J. R. (1980) · Behavioral and Brain Sciences · doi:10.1017/s0140525x00005756 · Cited by 6,954 · cited 3×
“Some researchers have argued that LMs are ‘‘all syntax, no semantics’’, i.e., that they learn form, but not meaning (Searle, 1980; Bender and Koller, 2020; Marcus et al., 2023).”
BackgroundEmerging Properties in Self-Supervised Vision Transformers
Caron, M., Touvron, H., Misra, I., Jegou, H., Mairal, J., Bojanowski, P., & Joulin, A. (2021) · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.00951 · Cited by 5,638
Research works printed but not linked: 3
- Bird, 2009, Natural language processing with Python: Analyzing text with the natural language toolkit
- Dosovitskiy, 2021, An image is worth 16x16 words: Transformers for image recognition at scale
- Marconi, 1997, Lexical Competence
Cited by
Understanding World or Predicting Future? A Comprehensive Survey of World Models
Ding, J., Zhang, Y., Shang, Y., Zhang, Y., Zong, Z., Feng, J., Yuan, Y., Su, H., Li, N., Sukiennik, N., et al. (2026) · ACM Computing Surveys · doi:10.1145/3746449 · Cited by 169
“Also, Li et al.[143] demonstrate that language models partially converge towards representations isomorphic to those of vision models.”
Why concepts are (probably) vectors
Piantadosi, S. T., Muller, D. C. Y., Rule, J., Kaushik, K., Gorenstein, M. I., Leib, E. R., & Sanford, E. M. (2024) · Trends in Cognitive Sciences · doi:10.1016/j.tics.2024.06.011 · Cited by 86
Takata, R., Masumori, A., & Ikegami, T. (2024) · Entropy · doi:10.3390/e26121092 · Cited by 37
What Do Language Models Hear? Probing for Auditory Representations in Language Models
Ngo, J., & Kim, Y. (2024) · Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/2024.acl-long.297 · Cited by 5
Cao, X., Li, J., Ying, T., & Liu, Z. (2026) · Information Processing & Management · doi:10.1016/j.ipm.2026.105028 · Cited by 3
Self-citation
Metadata
- Authors
- Li, J., Kementchedjhieva, Y., Fierro, C., & Søgaard, A.
- Affiliations
- University of Copenhagen (DK)
- Mohamed bin Zayed University of Artificial Intelligence (AE)
- Venue
- Transactions of the Association for Computational Linguistics
- Publisher
- MIT Press
- Published
- 2024
- Volume
- 12
- Pages
- 1232-1249
- ISSN
- 2307-387X (ISSN-L)
- OpenAlex
- W4403051422
- Cited by
- 6
- References
- 73
- Citations by year
- 2026: 2 · 2025: 2 · 2024: 2
- FWCI
- 0.84
- Type
- journal article
- Language
- en
- Open access
- diamond
- doi.org
- Locations
- Transactions of the Association for Computational Linguistics (publishedVersion, cc-by)
- Research at the University of Copenhagen (University of Copenhagen) (publishedVersion, cc-by)
- arXiv (Cornell University) (submittedVersion, cc-by)
- Research at the University of Copenhagen (University of Copenhagen) (submittedVersion, cc-by)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion)
- arXiv (Cornell University) (cc-by)
- Funders
- Danmarks Grundforskningsfond
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Multimodal Machine Learning Applications
- Physical Sciences › Computer Science › Artificial Intelligence › Topic Modeling
- Physical Sciences › Computer Science › Artificial Intelligence › Natural Language Processing Techniques
- Keywords
- language models, vision models, shared representations, conceptual representation, pre-trained language models, vision transformer, multimodal representation, polysemy, word frequency, language comprehension, BERT, GPT-2, OPT, Llama 2, ResNet, SegFormer, MAE
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Do Vision and Language Models Share Concepts? A Vector Space Alignment Study. https://app.cochat.ai/papers/10.1162/tacl_a_00698
- The paper
- Li, J., Kementchedjhieva, Y., Fierro, C., & Søgaard, A. (2024). Do Vision and Language Models Share Concepts? A Vector Space Alignment Study. Transactions of the Association for Computational Linguistics. https://doi.org/10.1162/tacl_a_00698
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.