pith. sign in

arxiv: 2109.06129 · v2 · pith:EE2WUYBFnew · submitted 2021-09-13 · 💻 cs.CV · cs.CL

Can Language Models Encode Perceptual Structure Without Grounding? A Case Study in Color

classification 💻 cs.CV cs.CL
keywords coloralignmentdifferencesmodelsperceptualspacestructurecase
0
0 comments X
read the original abstract

Pretrained language models have been shown to encode relational information, such as the relations between entities or concepts in knowledge-bases -- (Paris, Capital, France). However, simple relations of this type can often be recovered heuristically and the extent to which models implicitly reflect topological structure that is grounded in world, such as perceptual structure, is unknown. To explore this question, we conduct a thorough case study on color. Namely, we employ a dataset of monolexemic color terms and color chips represented in CIELAB, a color space with a perceptually meaningful distance metric. Using two methods of evaluating the structural alignment of colors in this space with text-derived color term representations, we find significant correspondence. Analyzing the differences in alignment across the color spectrum, we find that warmer colors are, on average, better aligned to the perceptual color space than cooler ones, suggesting an intriguing connection to findings from recent work on efficient communication in color naming. Further analysis suggests that differences in alignment are, in part, mediated by collocationality and differences in syntactic usage, posing questions as to the relationship between color perception and usage and context.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 5 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. World Models in Pieces: Structural Certification for General Agents

    cs.AI 2026-06 unverdicted novelty 7.0

    Structural certification maps bounded goal-conditioned performance to O(1/n) + O(δ) entry-wise error bounds on an agent's internal world model for transitions filtered by deep compositional goals.

  2. When Do LLM Personas Support Visualization Design? A Cross-Model Study of Color Assignment and Chart Choice

    cs.HC 2026-07 unverdicted novelty 6.0

    LLM personas exhibit model-dependent personality effects on color choices and context-driven chart preferences, limiting their use as direct substitutes for human participants in visualization design.

  3. A Systematic Study of Behavioral Cloning for Scientific Data Annotation

    cs.HC 2026-05 unverdicted novelty 6.0

    Introduces 9 synthetic annotation tasks and benchmarks for behavioral cloning, finding hierarchical skill learning, scaling benefits, effective multi-task pretraining, and shared internal representations of task phase...

  4. The Platonic Representation Hypothesis

    cs.LG 2024-05 unverdicted novelty 5.0

    Representations learned by large AI models are converging toward a shared statistical model of reality.

  5. Geometry of Human Perceptual Domains Emerges Transiently in LLM Representations

    cs.AI 2026-05 unverdicted novelty 4.0

    Perceptual geometry for color, pitch, emotion and taste emerges transiently in intermediate layers of transformer LLMs despite purely textual training.