Culturally transmitted color categories in LLMs reflect a learning bias toward efficient compression
This addresses the problem of understanding if LLMs can replicate human cognitive biases in semantic categorization, with implications for AI and cognitive science, though it is incremental in applying known principles to new models.
The study investigated whether large language models (LLMs) can develop efficient, human-like semantic systems for color categories, finding that LLMs like Gemini 2.0-flash align well with English color-naming patterns and achieve high IB-efficiency scores, and through simulated cultural evolution, they restructure random systems toward greater efficiency and cross-linguistic alignment.
Converging evidence suggests that systems of semantic categories across human languages achieve near-optimal compression via the Information Bottleneck (IB) complexity-accuracy principle. Large language models (LLMs) are not trained for this objective, which raises the question: are LLMs capable of evolving efficient human-like semantic systems? To address this question, we focus on the domain of color as a key testbed of cognitive theories of categorization and replicate with LLMs (Gemini 2.0-flash and Llama 3.3-70B-Instruct) two influential human behavioral studies. First, we conduct an English color-naming study, showing that Gemini aligns well with the naming patterns of native English speakers and achieves a significantly high IB-efficiency score, while Llama exhibits an efficient but lower complexity system compared to English. Second, to test whether LLMs simply mimic patterns in their training data or actually exhibit a human-like inductive bias toward IB-efficiency, we simulate cultural evolution of pseudo color-naming systems in LLMs via iterated in-context language learning. We find that akin to humans, LLMs iteratively restructure initially random systems towards greater IB-efficiency and increased alignment with patterns observed across the world's languages. These findings demonstrate that LLMs are capable of evolving perceptually grounded, human-like semantic systems, driven by the same fundamental principle that governs semantic efficiency across human languages.