Computational Lesions in Multilingual Language Models Separate Shared and Language-specific Brain Alignment

• URL: http://arxiv.org/abs/2604.10627v1
• Date: Sun, 12 Apr 2026 13:06:47 GMT
• Title: Computational Lesions in Multilingual Language Models Separate Shared and Language-specific Brain Alignment
• Abstract summary: 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.
• Score: 43.72658186052991
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: How the brain supports language across different languages is a basic question in neuroscience and a useful test for multilingual artificial intelligence. Neuroimaging has identified language-responsive brain regions across languages, but it cannot by itself show whether the underlying processing is shared or language-specific. Here we use six multilingual large language models (LLMs) as controllable systems and create targeted ``computational lesions'' by zeroing small parameter sets that are important across languages or especially important for one language. We then 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 (112 participants). Lesioning a compact shared core reduces whole-brain encoding correlation by 60.32% relative to intact models, whereas language-specific lesions preserve cross-language separation in embedding space but selectively weaken brain predictivity for the matched native language. These results support a shared backbone with embedded specializations and provide a causal framework for studying multilingual brain-model alignment.

Related papers

• Distribution-aware Language Neuron Identification in Multilingual Large Language Models [11.749671657167966]
  Existing work measures language specificity using the entropy of each neuron's language-wise probabilities of being active.<n>We propose Distribution-aware Language Neuron selection, which leverages pairwise relationships between per-language activation distributions.<n>Our identifier more effectively isolates language-specific causal effects, yielding up to 4.9$times$ higher on-target language damage per neuron.
  arXiv  Detail & Related papers  (2026-09-10T02:12:52Z)
• Multilingual Emotion Neurons in Large Audio-Language Models [15.987865011030387]
  Emotion is central to human communication, and its expression varies across languages.<n>It remains unclear whether large audio-language models (LALMs) encode emotion through language-specific correlations or language-agnostic representations.<n>We present the first neuron-level interpretability study of this question.
  arXiv  Detail & Related papers  (2026-08-09T15:42:55Z)
• Language Arithmetics: Towards Systematic Language Neuron Identification and Manipulation [9.518772041855923]
  We analyze language-specific neurons in Llama-3.1-8B, Mistral-Nemo-12B, and Aya-Expanse-8B & 32B across 21 typologically diverse languages.<n>We show that these neurons cluster in deeper layers, with non-Latin scripts showing greater specialization.<n>We steer models to deactivate unwanted languages and activate desired ones, outperforming simpler replacement approaches.
  arXiv  Detail & Related papers  (2025-07-30T12:23:39Z)
• 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 [85.0284555835015]
  Large language models (LLMs) have revolutionized the field of natural language processing (NLP)<n>Few studies have attempted to explore the internal workings of LLMs in multilingual settings.<n>We classify neurons into four distinct categories based on their responses to a specific input across different languages.
  arXiv  Detail & Related papers  (2024-06-13T16:04:11Z)
• BrainLLM: Generative Language Decoding from Brain Recordings [77.66707255697706]
  We propose a generative language BCI that utilizes the capacity of a large language model and a semantic brain decoder.<n>The proposed model can generate coherent language sequences aligned with the semantic content of visual or auditory language stimuli.<n>Our findings demonstrate the potential and feasibility of employing BCIs in direct language generation.
  arXiv  Detail & Related papers  (2023-11-16T13:37:21Z)
• Joint processing of linguistic properties in brains and language models [14.997785690790032]
  We investigate the correspondence between the detailed processing of linguistic information by the human brain versus language models. We find that elimination of specific linguistic properties results in a significant decrease in brain alignment. These findings provide clear evidence for the role of specific linguistic information in the alignment between brain and language models.
  arXiv  Detail & Related papers  (2022-12-15T19:13:42Z)
• 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)
• Low-Dimensional Structure in the Space of Language Representations is Reflected in Brain Responses [62.197912623223964]
  We show a low-dimensional structure where language models and translation models smoothly interpolate between word embeddings, syntactic and semantic tasks, and future word embeddings. We find that this representation embedding can predict how well each individual feature space maps to human brain responses to natural language stimuli recorded using fMRI. This suggests that the embedding captures some part of the brain's natural language representation structure.
  arXiv  Detail & Related papers  (2021-06-09T22:59:12Z)
• Does injecting linguistic structure into language models lead to better alignment with brain recordings? [13.880819301385854]
  We evaluate whether language models align better with brain recordings if their attention is biased by annotations from syntactic or semantic formalisms. Our proposed approach enables the evaluation of more targeted hypotheses about the composition of meaning in the brain.
  arXiv  Detail & Related papers  (2021-01-29T14:42:02Z)
• Bridging Linguistic Typology and Multilingual Machine Translation with Multi-View Language Representations [83.27475281544868]
  We use singular vector canonical correlation analysis to study what kind of information is induced from each source. We observe that our representations embed typology and strengthen correlations with language relationships. We then take advantage of our multi-view language vector space for multilingual machine translation, where we achieve competitive overall translation accuracy.
  arXiv  Detail & Related papers  (2020-04-30T16:25:39Z)

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.