Distribution-aware Language Neuron Identification in Multilingual Large Language Models

• URL: http://arxiv.org/abs/2609.10993v1
• Date: Thu, 10 Sep 2026 02:12:52 GMT
• Title: Distribution-aware Language Neuron Identification in Multilingual Large Language Models
• Abstract summary: 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.
• Score: 11.749671657167966
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Multilingual large language models (mLLMs) contain a small fraction of feed-forward neurons that are sensitive to particular languages, commonly termed language-specific neurons. Existing work measures language specificity using the entropy of each neuron's language-wise probabilities of being active, where a neuron is considered active when its activation value is positive. However, this approach may not fully capture the multilingual nature of mLLMs, where language representations are distributional and mutually related. We propose Distribution-aware Language Neuron selection, which leverages pairwise relationships between per-language activation distributions over the full activation range, including negative values. Specifically, we quantify each neuron's language specificity by clustering languages using pairwise overlap coefficients between their activation distributions. Across two mLLMs and two held-out corpora, our identifier more effectively isolates language-specific causal effects, yielding up to 4.9$\times$ higher on-target language damage per neuron while preserving off-target language performance.

Related papers

• 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)
• CRANE: Causal Relevance Analysis of Language-Specific Neurons in Multilingual Large Language Models [0.021485350418225243]
  How language capabilities are organized at the neuron level remains poorly understood.<n>We propose CRANE, a relevance-based analysis framework that redefines language specificity in terms of functional necessity.
  arXiv  Detail & Related papers  (2026-01-08T07:21:13Z)
• 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)
• The Emergence of Abstract Thought in Large Language Models Beyond Any Language [95.50197866832772]
  Large language models (LLMs) function effectively across a diverse range of languages.<n>Preliminary studies observe that the hidden activations of LLMs often resemble English, even when responding to non-English prompts.<n>Recent results show strong multilingual performance, even surpassing English performance on specific tasks in other languages.
  arXiv  Detail & Related papers  (2025-06-11T16:00:54Z)
• 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)
• Mechanistic Understanding and Mitigation of Language Confusion in English-Centric Large Language Models [56.61984030508691]
  We present the first mechanistic interpretability study of language confusion.<n>We show that confusion points (CPs) are central to this phenomenon.<n>We show that editing a small set of critical neurons, identified via comparative analysis with a multilingual-tuned counterpart, substantially mitigates confusion.
  arXiv  Detail & Related papers  (2025-05-22T11:29:17Z)
• Language-specific Neurons Do Not Facilitate Cross-Lingual Transfer [21.205821852762362]
  Existing techniques to identify language-specific neurons can be leveraged to enhance cross-lingual task performance of lowresource languages.<n>We find that such neuron-specific interventions are insufficient to yield cross-lingual improvements on downstream tasks.
  arXiv  Detail & Related papers  (2025-03-21T18:08:11Z)
• 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)
• 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)
• 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.