Neuron-Level Analysis of Cultural Understanding in Large Language Models

• URL: http://arxiv.org/abs/2510.08284v1
• Date: Thu, 09 Oct 2025 14:35:00 GMT
• Title: Neuron-Level Analysis of Cultural Understanding in Large Language Models
• Abstract summary: Large language models (LLMs) are increasingly deployed worldwide, ensuring their fair and comprehensive cultural understanding.<n>We conduct a neuron-level analysis to identify neurons that drive cultural behavior.<n>We identify both culture-general neurons contributing to cultural understanding regardless of cultures, and culture-specific neurons tied to an individual culture.
• Score: 34.65197313327234
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: As large language models (LLMs) are increasingly deployed worldwide, ensuring their fair and comprehensive cultural understanding is important. However, LLMs exhibit cultural bias and limited awareness of underrepresented cultures, while the mechanisms underlying their cultural understanding remain underexplored. To fill this gap, we conduct a neuron-level analysis to identify neurons that drive cultural behavior, introducing a gradient-based scoring method with additional filtering for precise refinement. We identify both culture-general neurons contributing to cultural understanding regardless of cultures, and culture-specific neurons tied to an individual culture. These neurons account for less than 1% of all neurons and are concentrated in shallow to middle MLP layers. We validate their role by showing that suppressing them substantially degrades performance on cultural benchmarks (by up to 30%), while performance on general natural language understanding (NLU) benchmarks remains largely unaffected. Moreover, we show that culture-specific neurons support knowledge of not only the target culture, but also related cultures. Finally, we demonstrate that training on NLU benchmarks can diminish models' cultural understanding when we update modules containing many culture-general neurons. These findings provide insights into the internal mechanisms of LLMs and offer practical guidance for model training and engineering. Our code is available at https://github.com/ynklab/CULNIG

Related papers

• CultureForest: Understanding and Evaluating Cultural Norm Grounded Reasoning in LLMs [59.09971492475217]
  We introduce CultureForest, a benchmark for textitCultural Norm Grounded Reasoning<n>CultureForest comprises 5,378 examples across 8 domains and 53 countries/regions.<n>Extensive experiments reveal that even top-tier models degrade substantially in open-ended settings.
  arXiv  Detail & Related papers  (2026-06-01T08:25:12Z)
• LLMs as Cultural Archives: Cultural Commonsense Knowledge Graph Extraction [57.23766971626989]
  Large language models (LLMs) encode rich cultural knowledge learned from diverse web-scale data.<n>We present an iterative, prompt-based framework for constructing a Cultural Commonsense Knowledge Graph (CCKG)<n>We find that the cultural knowledge graphs are better realized in English, even when the target culture is non-English.
  arXiv  Detail & Related papers  (2026-01-25T20:05:04Z)
• Finding Culture-Sensitive Neurons in Vision-Language Models [20.13200214439683]
  We study the presence of culture-sensitive neurons in vision-language models (VLMs)<n>We identify neurons of culture selectivity and perform causal tests by deactivating the neurons flagged by different identification methods.<n>Our findings shed new light on the internal organization of multimodal representations.
  arXiv  Detail & Related papers  (2025-10-28T20:14:37Z)
• CultureScope: A Dimensional Lens for Probing Cultural Understanding in LLMs [57.653830744706305]
  CultureScope is the most comprehensive evaluation framework to date for assessing cultural understanding in large language models.<n>Inspired by the cultural iceberg theory, we design a novel dimensional schema for cultural knowledge classification.<n> Experimental results demonstrate that our method can effectively evaluate cultural understanding.
  arXiv  Detail & Related papers  (2025-09-19T17:47:48Z)
• Entangled in Representations: Mechanistic Investigation of Cultural Biases in Large Language Models [42.367959511140036]
  We propose Culturescope, the first interpretability-based method that probes the internal representations of large language models.<n>We introduce a cultural flattening score as a measure of the intrinsic cultural biases.<n>Our experimental results reveal that LLMs encode Western-dominance bias and cultural flattening in their cultural knowledge space.
  arXiv  Detail & Related papers  (2025-08-12T12:05:32Z)
• Culture is Not Trivia: Sociocultural Theory for Cultural NLP [10.76392030245232]
  We argue that these methodological limitations are symptomatic of a theoretical gap.<n>We draw on a well-developed theory of culture from sociocultural linguistics to fill this gap.
  arXiv  Detail & Related papers  (2025-02-17T17:25:11Z)
• CultureVLM: Characterizing and Improving Cultural Understanding of Vision-Language Models for over 100 Countries [63.00147630084146]
  Vision-language models (VLMs) have advanced human-AI interaction but struggle with cultural understanding.<n>CultureVerse is a large-scale multimodal benchmark covering 19, 682 cultural concepts, 188 countries/regions, 15 cultural concepts, and 3 question types.<n>We propose CultureVLM, a series of VLMs fine-tuned on our dataset to achieve significant performance improvement in cultural understanding.
  arXiv  Detail & Related papers  (2025-01-02T14:42:37Z)
• Navigating the Cultural Kaleidoscope: A Hitchhiker's Guide to Sensitivity in Large Language Models [4.771099208181585]
  LLMs are increasingly deployed in global applications, ensuring users from diverse backgrounds feel respected and understood.<n>Cultural harm can arise when these models fail to align with specific cultural norms, resulting in misrepresentations or violations of cultural values.<n>We present two key contributions: A cultural harm test dataset, created to assess model outputs across different cultural contexts through scenarios that expose potential cultural insensitivities, and a culturally aligned preference dataset, aimed at restoring cultural sensitivity through fine-tuning based on feedback from diverse annotators.
  arXiv  Detail & Related papers  (2024-10-15T18:13:10Z)
• CULTURE-GEN: Revealing Global Cultural Perception in Language Models through Natural Language Prompting [73.94059188347582]
  We uncover culture perceptions of three SOTA models on 110 countries and regions on 8 culture-related topics through culture-conditioned generations. We discover that culture-conditioned generation consist of linguistic "markers" that distinguish marginalized cultures apart from default cultures.
  arXiv  Detail & Related papers  (2024-04-16T00:50:43Z)
• Not All Countries Celebrate Thanksgiving: On the Cultural Dominance in Large Language Models [89.94270049334479]
  This paper identifies a cultural dominance issue within large language models (LLMs) LLMs often provide inappropriate English-culture-related answers that are not relevant to the expected culture when users ask in non-English languages.
  arXiv  Detail & Related papers  (2023-10-19T05:38:23Z)

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.