Abstract
Visual distinctions are often finer than those reflected in linguistic conceptualization. Vision-language models exhibit a similar asymmetry: a distinction can remain discriminable in frozen image geometry while being weakly addressable through the native text interface. We study this gap by separating visual discriminability from linguistic addressability in text-to-image retrieval. Using FactorAtlas, a fully crossed testbed of 23,040 images spanning shape, hue, pattern, and nuisance variation, we compare both readouts on held-out images of the same distinctions. We then derive image-side contrasts that separate each value from its alternatives for matched visual grounding, and test whether this reduces the native-text access gap across factors and models. Direction-specific and visual-absence controls tie these gains to the relevant visual contrast; the gains persist after global alignment and extend to compositional retrieval and natural images. Together, these results show that visual discriminability and linguistic addressability need not coincide, and that matched visual grounding can probe and reduce the resulting access gap.
Keywords
Publication details
- Journal
- Not available
- Open access
- Green open access
Cite this article
APA 7
Jeon, W., Yang, J., Chung, S., & Kim, T. (2026). Seeing Is Not Addressing: Auditing Linguistic Access to Frozen Visual Geometry. https://omanscience.com/en/articles/seeing-is-not-addressing-auditing-linguistic-access-to-frozen-visual-geometry
MLA 9
Jeon, Woosang, et al. "Seeing Is Not Addressing: Auditing Linguistic Access to Frozen Visual Geometry." https://omanscience.com/en/articles/seeing-is-not-addressing-auditing-linguistic-access-to-frozen-visual-geometry.
Chicago (author–date)
Jeon, Woosang, Jiwon Yang, Soo Chung, and Taehyeong Kim. 2026. "Seeing Is Not Addressing: Auditing Linguistic Access to Frozen Visual Geometry." https://omanscience.com/en/articles/seeing-is-not-addressing-auditing-linguistic-access-to-frozen-visual-geometry.
Harvard
Jeon, W., Yang, J., Chung, S. and Kim, T. (2026) 'Seeing Is Not Addressing: Auditing Linguistic Access to Frozen Visual Geometry', Available at: https://omanscience.com/en/articles/seeing-is-not-addressing-auditing-linguistic-access-to-frozen-visual-geometry.
Vancouver
Jeon W, Yang J, Chung S, Kim T. Seeing Is Not Addressing: Auditing Linguistic Access to Frozen Visual Geometry. https://omanscience.com/en/articles/seeing-is-not-addressing-auditing-linguistic-access-to-frozen-visual-geometry
IEEE
W. Jeon, J. Yang, S. Chung, and T. Kim, "Seeing Is Not Addressing: Auditing Linguistic Access to Frozen Visual Geometry," https://omanscience.com/en/articles/seeing-is-not-addressing-auditing-linguistic-access-to-frozen-visual-geometry.