Can Language Models Encode Perceptual Structure Without Grounding? A Case Study in Color
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.
Forward citations
Cited by 5 Pith papers
-
World Models in Pieces: Structural Certification for General Agents
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.
-
When Do LLM Personas Support Visualization Design? A Cross-Model Study of Color Assignment and Chart Choice
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.
-
A Systematic Study of Behavioral Cloning for Scientific Data Annotation
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...
-
The Platonic Representation Hypothesis
Representations learned by large AI models are converging toward a shared statistical model of reality.
-
Geometry of Human Perceptual Domains Emerges Transiently in LLM Representations
Perceptual geometry for color, pitch, emotion and taste emerges transiently in intermediate layers of transformer LLMs despite purely textual training.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.