Distribution-aware Language Neuron Identification in Multilingual Large Language Models — Paper

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.

Authors 6

Minjun Kim, Inho Won, Junghun Yuk, Dongyeon Kim, Jihyo Kim, KyungTae Lim

Specification

Official page: arxiv.org/abs/2609.10993
Source:arXiv (Atom API + RSS)T1observed 6 h agohigh
Arxiv announce type: new
Source:arXiv (Atom API + RSS)T1observed 6 h agohigh
arXiv id: 2609.10993
Source:arXiv (Atom API + RSS)T1observed 6 h agohigh
Categories: cs.CL
Source:arXiv (Atom API + RSS)T1observed 6 h agohigh
PDF: arxiv.org/pdf/2609.10993
Source:arXiv (Atom API + RSS)T1observed 6 h agohigh
Primary category: cs.CL
Source:arXiv (Atom API + RSS)T1observed 6 h agohigh
Published: 11 Sept 2026
Source:arXiv (Atom API + RSS)T1observed 6 h agohigh

Each value shows its source, tier and observation time. Conflicting claims are kept side by side and flagged — never averaged. How AI Atlas records facts →

Provenance

Attributed facts

9

Source tiers

T19

Freshest observation

6 h ago

Conflicts

None

No models linked to this paper yet.

Authors: Minjun Kim, Inho Won, Junghun Yuk

As of

Rewind the record: see this entity's attributes exactly as AI Atlas knew them on a given day.

Claim history · Authors

1 claims · 1 propertiesShow all properties

Authorsauthors1

Claim history for Authors
Value	Valid from → to	Status	Source	Confidence	Extractor
Minjun Kim, Inho Won, Junghun Yuk, Dongyeon Kim, Jihyo Kim, KyungTae Lim	11 Sept 2026 21:03 UTC → current	current	arXiv (Atom API + RSS)T1	high	deterministic

Claims are temporal and append-only: a new observation closes the previous claim (valid_to) instead of overwriting it. Conflicting claims from different sources are kept side by side and flagged — never averaged. Methodology →

11 Sept 2026
New paperPaperDistribution-aware Language Neuron Identification in Multilingual Large Language Models
New paper: Distribution-aware Language Neuron Identification in Multilingual Large Language Models
arxiv
rss.arxiv.org

Full timeline →

Source documents
Source	Document	Type	Tier	Last observed	Snapshots
arXiv (Atom API + RSS)	rss.arxiv.org/rss/cs.CL	feed	T1· Official	4 h ago	1

Tier 1 = official/primary, 2 = quality secondary, 3 = community, 4 = unverified. Every snapshot is archived; see all sources and the methodology.