Cover Image

The Transfer Neurons Hypothesis: An Underlying Mechanism for Language Latent Space Transitions in Multilingual LLMs

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Tezuka, Hinata, Inoue, Naoya
Format:	Preprint
Published:	2025
Subjects:	Computation and Language Artificial Intelligence Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Debiasing Multilingual LLMs in Cross-lingual Latent Space
by: Peng, Qiwei, et al.
Published: (2025)

Mechanism of Task-oriented Information Removal in In-context Learning
by: Cho, Hakaze, et al.
Published: (2025)

Code-Switching Curriculum Learning for Multilingual Transfer in LLMs
by: Yoo, Haneul, et al.
Published: (2024)

Revisiting In-context Learning Inference Circuit in Large Language Models
by: Cho, Hakaze, et al.
Published: (2024)

Identifying the Correlation Between Language Distance and Cross-Lingual Transfer in a Multilingual Representation Space
by: Philippy, Fred, et al.
Published: (2023)

Language-specific Neurons Do Not Facilitate Cross-Lingual Transfer
by: Mondal, Soumen Kumar, et al.
Published: (2025)

Binary Autoencoder for Mechanistic Interpretability of Large Language Models
by: Cho, Hakaze, et al.
Published: (2025)

Analyzing the Evaluation of Cross-Lingual Knowledge Transfer in Multilingual Language Models
by: Rajaee, Sara, et al.
Published: (2024)

LatentBreak: Jailbreaking Large Language Models through Latent Space Feedback
by: Mura, Raffaele, et al.
Published: (2025)

Affinity and Diversity: A Unified Metric for Demonstration Selection via Internal Representations
by: Kato, Mariko, et al.
Published: (2025)

Leveraging Parameter Space Symmetries for Reasoning Skill Transfer in LLMs
by: Horoi, Stefan, et al.
Published: (2025)

Prompting with Phonemes: Enhancing LLMs' Multilinguality for Non-Latin Script Languages
by: Nguyen, Hoang H, et al.
Published: (2024)

NeuronTune: Fine-Grained Neuron Modulation for Balanced Safety-Utility Alignment in LLMs
by: Pan, Birong, et al.
Published: (2025)

NEAT: Concept driven Neuron Attribution in LLMs
by: Kavuri, Vivek Hruday, et al.
Published: (2025)

RLHF Can Speak Many Languages: Unlocking Multilingual Preference Optimization for LLMs
by: Dang, John, et al.
Published: (2024)

Do Multilingual LLMs Think In English?
by: Schut, Lisa, et al.
Published: (2025)

Mechanistic Fine-tuning for In-context Learning
by: Cho, Hakaze, et al.
Published: (2025)

Understanding Token Probability Encoding in Output Embeddings
by: Cho, Hakaze, et al.
Published: (2024)

Linear Representation Transferability Hypothesis: Leveraging Small Models to Steer Large Models
by: Bello, Femi, et al.
Published: (2025)

Hypothesis Search: Inductive Reasoning with Language Models
by: Wang, Ruocheng, et al.
Published: (2023)

Confidence Regulation Neurons in Language Models
by: Stolfo, Alessandro, et al.
Published: (2024)

Understanding Jailbreak Success: A Study of Latent Space Dynamics in Large Language Models
by: Ball, Sarah, et al.
Published: (2024)

The Consistency Hypothesis in Uncertainty Quantification for Large Language Models
by: Xiao, Quan, et al.
Published: (2025)

Hypothesis Generation and Inductive Inference in Children and Language Models
by: Qin, Jeffrey, et al.
Published: (2026)

The Linear Representation Hypothesis and the Geometry of Large Language Models
by: Park, Kiho, et al.
Published: (2023)

Token-based Decision Criteria Are Suboptimal in In-context Learning
by: Cho, Hakaze, et al.
Published: (2024)

MENTIS: What Belief Changes Under Alignment? Measuring Multi-Scale Latent Torsion in Language Models
by: Saha, Partha Pratim, et al.
Published: (2026)

Universal Neurons in GPT2 Language Models
by: Gurnee, Wes, et al.
Published: (2024)

Disentangling the Roles of Target-Side Transfer and Regularization in Multilingual Machine Translation
by: Meng, Yan, et al.
Published: (2024)

Steering into New Embedding Spaces: Analyzing Cross-Lingual Alignment Induced by Model Interventions in Multilingual Language Models
by: Sundar, Anirudh, et al.
Published: (2025)

Local Topology Measures of Contextual Language Model Latent Spaces With Applications to Dialogue Term Extraction
by: Ruppik, Benjamin Matthias, et al.
Published: (2024)

HypoEval: Hypothesis-Guided Evaluation for Natural Language Generation
by: Li, Mingxuan, et al.
Published: (2025)

Sailor2: Sailing in South-East Asia with Inclusive Multilingual LLMs
by: Dou, Longxu, et al.
Published: (2025)

Hypothesis Generation with Large Language Models
by: Zhou, Yangqiaoyu, et al.
Published: (2024)

Bridging the Gap: Dynamic Learning Strategies for Improving Multilingual Performance in LLMs
by: Kumar, Somnath, et al.
Published: (2024)

Finding Culture-Sensitive Neurons in Vision-Language Models
by: Zhao, Xiutian, et al.
Published: (2025)

Deliberation in Latent Space via Differentiable Cache Augmentation
by: Liu, Luyang, et al.
Published: (2024)

Polysemy of Synthetic Neurons Towards a New Type of Explanatory Categorical Vector Spaces
by: Pichat, Michael, et al.
Published: (2025)

Towards Multilingual LLM Evaluation for European Languages
by: Thellmann, Klaudia, et al.
Published: (2024)

Do LLMs Recognize Your Latent Preferences? A Benchmark for Latent Information Discovery in Personalized Interaction
by: Tsaknakis, Ioannis, et al.
Published: (2025)