Isolating Culture Neurons in Multilingual Large Language Models

• URL: http://arxiv.org/abs/2508.02241v1
• Date: Mon, 04 Aug 2025 09:41:10 GMT
• Title: Isolating Culture Neurons in Multilingual Large Language Models
• Abstract summary: We identify language-specific neurons and extend it to localize and isolate culture-specific neurons.<n>To facilitate our experiments, we introduce MUREL, a curated dataset of 85.2 million tokens spanning six different cultures.<n>Our localization and intervention experiments show that LLMs encode different cultures in distinct neuron populations, predominantly in upper layers.
• Score: 4.14360329494344
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Language and culture are deeply intertwined, yet it is so far unclear how and where multilingual large language models encode culture. Here, we extend upon an established methodology for identifying language-specific neurons and extend it to localize and isolate culture-specific neurons, carefully disentangling their overlap and interaction with language-specific neurons. To facilitate our experiments, we introduce MUREL, a curated dataset of 85.2 million tokens spanning six different cultures. Our localization and intervention experiments show that LLMs encode different cultures in distinct neuron populations, predominantly in upper layers, and that these culture neurons can be modulated independently from language-specific neurons or those specific to other cultures. These findings suggest that cultural knowledge and propensities in multilingual language models can be selectively isolated and edited - promoting fairness, inclusivity, and alignment. Code and data is available at https://github.com/namazifard/Culture_Neurons .

Related papers

• Computational Lesions in Multilingual Language Models Separate Shared and Language-specific Brain Alignment [43.72658186052991]
  How the brain supports language across different languages is a basic question in neuroscience and a useful test for multilingual artificial intelligence.<n>Here we use six multilingual large language models (LLMs) as controllable systems and create targeted computational lesions''<n>We compare intact and lesioned models in predicting functional magnetic resonance imaging (fMRI) responses during 100 minutes of naturalistic story listening in native English, Chinese and French.
  arXiv  Detail & Related papers  (2026-04-12T13:06:47Z)
• NeuronMoE: Neuron-Guided Mixture-of-Experts for Efficient Multilingual LLM Extension [16.52781433504377]
  Mixture-of-Experts (MoE) architectures address this by adding sparse language-specific parameters.<n>Current approaches allocate experts based on layer-level similarity, yet language processing exhibits fine-grained specialization at individual neurons.<n>We propose $textbfNeuronMoE$, a method that analyzes language-specific neurons across all transformer components to guide expert allocation per layer.
  arXiv  Detail & Related papers  (2026-03-05T10:55:26Z)
• Do You Know About My Nation? Investigating Multilingual Language Models' Cultural Literacy Through Factual Knowledge [68.6805229085352]
  Most multilingual question-answering benchmarks do not factor in regional diversity in the information they capture.<n>XNationQA encompasses a total of 49,280 questions on the geography, culture, and history of nine countries, presented in seven languages.<n>We benchmark eight standard multilingual LLMs on XNationQA and evaluate them using two novel transference metrics.
  arXiv  Detail & Related papers  (2025-11-01T18:41:34Z)
• 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)
• How does Alignment Enhance LLMs' Multilingual Capabilities? A Language Neurons Perspective [64.79894853375478]
  We propose a new finer-grained neuron identification algorithm, which detects language neurons(including language-specific neurons and language-related neurons) and language-agnostic neurons.<n>Based on the distributional characteristics of different types of neurons, we divide the LLMs' internal process for multilingual inference into four parts.<n>We systematically analyze the models before and after alignment with a focus on different types of neurons.
  arXiv  Detail & Related papers  (2025-05-27T17:59:52Z)
• Sharing Matters: Analysing Neurons Across Languages and Tasks in LLMs [70.3132264719438]
  We aim to fill the research gap by examining how neuron activation is shared across tasks and languages. We classify neurons into four distinct categories based on their responses to a specific input across different languages. Our analysis reveals the following insights: (i) the patterns of neuron sharing are significantly affected by the characteristics of tasks and examples; (ii) neuron sharing does not fully correspond with language similarity; (iii) shared neurons play a vital role in generating responses, especially those shared across all languages.
  arXiv  Detail & Related papers  (2024-06-13T16:04:11Z)
• The Echoes of Multilinguality: Tracing Cultural Value Shifts during LM Fine-tuning [23.418656688405605]
  We study how languages can exert influence on the cultural values encoded for different test languages, by studying how such values are revised during fine-tuning. Lastly, we use a training data attribution method to find patterns in the fine-tuning examples, and the languages that they come from, that tend to instigate value shifts.
  arXiv  Detail & Related papers  (2024-05-21T12:55:15Z)
• 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)
• On the Multilingual Ability of Decoder-based Pre-trained Language Models: Finding and Controlling Language-Specific Neurons [37.32174349956148]
  We analyze the neuron-level internal behavior of multilingual decoder-based language models (PLMs) We show that language-specific neurons are unique, with a slight overlap ( 5%) between languages. We tamper with less than 1% of the total neurons in each model during inference and demonstrate that tampering with a few language-specific neurons drastically changes the probability of target language occurrence in text generation.
  arXiv  Detail & Related papers  (2024-04-03T03:37:22Z)
• Revealing the Parallel Multilingual Learning within Large Language Models [50.098518799536144]
  In this study, we reveal an in-context learning capability of multilingual large language models (LLMs)<n>By translating the input to several languages, we provide Parallel Input in Multiple Languages (PiM) to LLMs, which significantly enhances their comprehension abilities.
  arXiv  Detail & Related papers  (2024-03-14T03:33:46Z)
• How do Large Language Models Handle Multilingualism? [81.15060972112563]
  This study explores how large language models (LLMs) handle multilingualism. LLMs initially understand the query, converting multilingual inputs into English for task-solving. In the intermediate layers, they employ English for thinking and incorporate multilingual knowledge with self-attention and feed-forward structures.
  arXiv  Detail & Related papers  (2024-02-29T02:55:26Z)
• Investigating Cultural Alignment of Large Language Models [10.738300803676655]
  We show that Large Language Models (LLMs) genuinely encapsulate the diverse knowledge adopted by different cultures. We quantify cultural alignment by simulating sociological surveys, comparing model responses to those of actual survey participants as references. We introduce Anthropological Prompting, a novel method leveraging anthropological reasoning to enhance cultural alignment.
  arXiv  Detail & Related papers  (2024-02-20T18:47:28Z)
• Multi-lingual and Multi-cultural Figurative Language Understanding [69.47641938200817]
  Figurative language permeates human communication, but is relatively understudied in NLP. We create a dataset for seven diverse languages associated with a variety of cultures: Hindi, Indonesian, Javanese, Kannada, Sundanese, Swahili and Yoruba. Our dataset reveals that each language relies on cultural and regional concepts for figurative expressions, with the highest overlap between languages originating from the same region. All languages exhibit a significant deficiency compared to English, with variations in performance reflecting the availability of pre-training and fine-tuning data.
  arXiv  Detail & Related papers  (2023-05-25T15:30:31Z)
• Same Neurons, Different Languages: Probing Morphosyntax in Multilingual Pre-trained Models [84.86942006830772]
  We conjecture that multilingual pre-trained models can derive language-universal abstractions about grammar. We conduct the first large-scale empirical study over 43 languages and 14 morphosyntactic categories with a state-of-the-art neuron-level probe.
  arXiv  Detail & Related papers  (2022-05-04T12:22:31Z)

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.