Cover Image

Language Lives in Sparse Dimensions: Toward Interpretable and Efficient Multilingual Control for Large Language Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zhong, Chengzhi, Cheng, Fei, Liu, Qianying, Murawaki, Yugo, Chu, Chenhui, Kurohashi, Sadao
Format:	Preprint
Published:	2025
Subjects:	Computation and Language Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Beyond English-Centric LLMs: What Language Do Multilingual Language Models Think in?
by: Zhong, Chengzhi, et al.
Published: (2024)

Assessing Agentic Large Language Models in Multilingual National Bias
by: Liu, Qianying, et al.
Published: (2025)

EMS: Efficient and Effective Massively Multilingual Sentence Embedding Learning
by: Mao, Zhuoyuan, et al.
Published: (2022)

Rapidly Developing High-quality Instruction Data and Evaluation Benchmark for Large Language Models with Minimal Human Effort: A Case Study on Japanese
by: Sun, Yikun, et al.
Published: (2024)

How Does Cognitive Bias Affect Large Language Models? A Case Study on the Anchoring Effect in Price Negotiation Simulations
by: Takenami, Yoshiki, et al.
Published: (2025)

Persona Jailbreaking in Large Language Models
by: Sandhan, Jivnesh, et al.
Published: (2026)

Reasoning Depth and Environment Complexity: A Controlled Study of RLVR Data Allocation across Logical Reasoning Tasks
by: Zhu, Yihua, et al.
Published: (2026)

A Joint Neural Baseline for Concept, Assertion, and Relation Extraction from Clinical Text
by: Cheng, Fei, et al.
Published: (2026)

Addressing Tokenization Inconsistency in Steganography and Watermarking Based on Large Language Models
by: Yan, Ruiyi, et al.
Published: (2025)

CAPE: Context-Aware Personality Evaluation Framework for Large Language Models
by: Sandhan, Jivnesh, et al.
Published: (2025)

Can We Trust LLM Detectors?
by: Sandhan, Jivnesh, et al.
Published: (2026)

Principal Component Analysis as a Sanity Check for Bayesian Phylolinguistic Reconstruction
by: Murawaki, Yugo
Published: (2024)

BIS Reasoning 1.0: The First Large-Scale Japanese Benchmark for Belief-Inconsistent Syllogistic Reasoning
by: Nguyen, Ha-Thanh, et al.
Published: (2025)

Reformulating Domain Adaptation of Large Language Models as Adapt-Retrieve-Revise: A Case Study on Chinese Legal Domain
by: wan, Zhen, et al.
Published: (2023)

Mechanistic Diagnostics of Spatial Lexical Bias in Multimodal Large Language Model Spatial Reasoning
by: Ma, Chuang, et al.
Published: (2026)

SpeechIQ: Speech-Agentic Intelligence Quotient Across Cognitive Levels in Voice Understanding by Large Language Models
by: Wan, Zhen, et al.
Published: (2025)

Investigating Cost-Efficiency of LLM-Generated Training Data for Conversational Semantic Frame Analysis
by: Matta, Shiho, et al.
Published: (2024)

Efficient Provably Secure Linguistic Steganography via Range Coding
by: Yan, Ruiyi, et al.
Published: (2026)

Memorization, Emergence, and Explaining Reversal Failures: A Controlled Study of Relational Semantics in LLMs
by: Zhu, Yihua, et al.
Published: (2026)

Cross-lingual Embedding Clustering for Hierarchical Softmax in Low-Resource Multilingual Speech Recognition
by: Yang, Zhengdong, et al.
Published: (2025)

Anchored Sliding Window: Toward Robust and Imperceptible Linguistic Steganography
by: Yan, Ruiyi, et al.
Published: (2026)

Towards Atoms of Large Language Models
by: Hu, Chenhui, et al.
Published: (2025)

SelfIE: Self-Interpretation of Large Language Model Embeddings
by: Chen, Haozhe, et al.
Published: (2024)

Efficient and Effective Vocabulary Expansion Towards Multilingual Large Language Models
by: Kim, Seungduk, et al.
Published: (2024)

Causal Language Control in Multilingual Transformers via Sparse Feature Steering
by: Chou, Cheng-Ting, et al.
Published: (2025)

MELD-ST: An Emotion-aware Speech Translation Dataset
by: Chen, Sirou, et al.
Published: (2024)

Reading Comprehension using Entity-based Memory Network
by: Wang, Xun, et al.
Published: (2016)

BayLing 2: A Multilingual Large Language Model with Efficient Language Alignment
by: Zhang, Shaolei, et al.
Published: (2024)

Safe-SAIL: Towards a Fine-grained Safety Landscape of Large Language Models via Sparse Autoencoder Interpretation Framework
by: Weng, Jiaqi, et al.
Published: (2025)

Towards Repository-Level Program Verification with Large Language Models
by: Zhong, Si Cheng, et al.
Published: (2025)

SparseDoctor: Towards Efficient Chat Doctor with Mixture of Experts Enhanced Large Language Models
by: Zhang, Jianbin, et al.
Published: (2025)

A Survey on Sparse Autoencoders: Interpreting the Internal Mechanisms of Large Language Models
by: Shu, Dong, et al.
Published: (2025)

Indic-TunedLens: Interpreting Multilingual Models in Indian Languages
by: Panchal, Mihir, et al.
Published: (2026)

Towards Understanding Multi-Round Large Language Model Reasoning: Approximability, Learnability and Generalizability
by: Xu, Chenhui, et al.
Published: (2025)

Focusing on Language: Revealing and Exploiting Language Attention Heads in Multilingual Large Language Models
by: Liu, Xin, et al.
Published: (2025)

Causal Tree Extraction from Medical Case Reports: A Novel Task for Experts-like Text Comprehension
by: Yahata, Sakiko, et al.
Published: (2025)

On the Alignment of Large Language Models with Global Human Opinion
by: Liu, Yang, et al.
Published: (2025)

All Languages Matter: On the Multilingual Safety of Large Language Models
by: Wang, Wenxuan, et al.
Published: (2023)

Multilingual Collaborative Defense for Large Language Models
by: Li, Hongliang, et al.
Published: (2025)

SLAM: Towards Efficient Multilingual Reasoning via Selective Language Alignment
by: Fan, Yuchun, et al.
Published: (2025)