Culturally transmitted color categories in LLMs reflect a learning bias toward efficient compression

• URL: http://arxiv.org/abs/2509.08093v2
• Date: Sun, 12 Oct 2025 20:33:56 GMT
• Title: Culturally transmitted color categories in LLMs reflect a learning bias toward efficient compression
• Abstract summary: We focus on the domain of color as a key testbed of cognitive theories of categorization.<n>We conduct an English color-naming study, showing that Gemini aligns well with the naming patterns of native English speakers.<n>We simulate cultural evolution of pseudo color-naming systems in large language models.
• Score: 2.3204178451683264
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: 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.

Related papers

• From Tokens to Thoughts: How LLMs and Humans Trade Compression for Meaning [63.25540801694765]
  Large Language Models (LLMs) demonstrate striking linguistic abilities, yet whether they achieve this same balance remains unclear.<n>We apply the Information Bottleneck principle to quantitatively compare how LLMs and humans navigate this compression-meaning trade-off.
  arXiv  Detail & Related papers  (2025-05-21T16:29:00Z)
• Explicit Learning and the LLM in Machine Translation [23.7663178803576]
  This study explores an LLM's ability to learn new languages using explanations found in a grammar book.<n>This ability, however, diminishes as the complexity of the linguistic phenomena to be learned increases.
  arXiv  Detail & Related papers  (2025-03-12T14:57:08Z)
• Disparities in LLM Reasoning Accuracy and Explanations: A Case Study on African American English [66.97110551643722]
  We investigate dialectal disparities in Large Language Models (LLMs) reasoning tasks.<n>We find that LLMs produce less accurate responses and simpler reasoning chains and explanations for AAE inputs.<n>These findings highlight systematic differences in how LLMs process and reason about different language varieties.
  arXiv  Detail & Related papers  (2025-03-06T05:15:34Z)
• VladVA: Discriminative Fine-tuning of LVLMs [67.14293827774827]
  Contrastively-trained Vision-Language Models (VLMs) like CLIP have become the de facto approach for discriminative vision-language representation learning.<n>We propose to combine "the best of both worlds": a new training approach for discriminative fine-tuning of LVLMs.
  arXiv  Detail & Related papers  (2024-12-05T17:54:27Z)
• Large Language Models as Neurolinguistic Subjects: Discrepancy between Performance and Competence [49.60849499134362]
  This study investigates the linguistic understanding of Large Language Models (LLMs) regarding signifier (form) and signified (meaning)<n>We introduce a neurolinguistic approach, utilizing a novel method that combines minimal pair and diagnostic probing to analyze activation patterns across model layers.<n>We found: (1) Psycholinguistic and neurolinguistic methods reveal that language performance and competence are distinct; (2) Direct probability measurement may not accurately assess linguistic competence; and (3) Instruction tuning won't change much competence but improve performance.
  arXiv  Detail & Related papers  (2024-11-12T04:16:44Z)
• Converging to a Lingua Franca: Evolution of Linguistic Regions and Semantics Alignment in Multilingual Large Language Models [11.423589362950812]
  Large language models (LLMs) have demonstrated remarkable performance, particularly in multilingual contexts.<n>Recent studies suggest that LLMs can transfer skills learned in one language to others, but the internal mechanisms behind this ability remain unclear.<n>This paper provides insights into the internal workings of LLMs, offering a foundation for future improvements in their cross-lingual capabilities.
  arXiv  Detail & Related papers  (2024-10-15T15:49:15Z)
• HLB: Benchmarking LLMs' Humanlikeness in Language Use [2.438748974410787]
  We present a comprehensive humanlikeness benchmark (HLB) evaluating 20 large language models (LLMs) We collected responses from over 2,000 human participants and compared them to outputs from the LLMs in these experiments. Our results reveal fine-grained differences in how well LLMs replicate human responses across various linguistic levels.
  arXiv  Detail & Related papers  (2024-09-24T09:02:28Z)
• Large Language Models are Interpretable Learners [53.56735770834617]
  In this paper, we show a combination of Large Language Models (LLMs) and symbolic programs can bridge the gap between expressiveness and interpretability. The pretrained LLM with natural language prompts provides a massive set of interpretable modules that can transform raw input into natural language concepts. As the knowledge learned by LSP is a combination of natural language descriptions and symbolic rules, it is easily transferable to humans (interpretable) and other LLMs.
  arXiv  Detail & Related papers  (2024-06-25T02:18:15Z)
• The Strong Pull of Prior Knowledge in Large Language Models and Its Impact on Emotion Recognition [74.04775677110179]
  In-context Learning (ICL) has emerged as a powerful paradigm for performing natural language tasks with Large Language Models (LLM) We show that LLMs have strong yet inconsistent priors in emotion recognition that ossify their predictions. Our results suggest that caution is needed when using ICL with larger LLMs for affect-centered tasks outside their pre-training domain.
  arXiv  Detail & Related papers  (2024-03-25T19:07:32Z)
• Instruction-tuning Aligns LLMs to the Human Brain [19.450164922129723]
  We investigate the effect of instruction-tuning on aligning large language models and human language processing mechanisms. We find that instruction-tuning generally enhances brain alignment, but has no similar effect on behavioral alignment. Our results suggest that the mechanisms that encode world knowledge in LLMs also improve representational alignment to the human brain.
  arXiv  Detail & Related papers  (2023-12-01T13:31:02Z)
• Large Language Models can Contrastively Refine their Generation for Better Sentence Representation Learning [57.74233319453229]
  Large language models (LLMs) have emerged as a groundbreaking technology and their unparalleled text generation capabilities have sparked interest in their application to the fundamental sentence representation learning task. We propose MultiCSR, a multi-level contrastive sentence representation learning framework that decomposes the process of prompting LLMs to generate a corpus. Our experiments reveal that MultiCSR enables a less advanced LLM to surpass the performance of ChatGPT, while applying it to ChatGPT achieves better state-of-the-art results.
  arXiv  Detail & Related papers  (2023-10-17T03:21:43Z)
• Cultural evolution via iterated learning and communication explains efficient color naming systems [1.0241134756773231]
  We consider efficiency as instantiated in the Information Bottleneck principle. We show that this model converges to color naming systems that are efficient in the IB sense. We conclude that the combination of iterated learning and communication provides a plausible means by which human semantic systems become efficient.
  arXiv  Detail & Related papers  (2023-05-17T12:18:44Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.