Cover Image

Uncovering Cross-Linguistic Disparities in LLMs using Sparse Autoencoders

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Xuan, Richmond Sin Jing, Huseynov, Jalil, Zhang, Yang
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

Constrain Alignment with Sparse Autoencoders
by: Yin, Qingyu, et al.
Published: (2024)

One Model, Many Morals: Uncovering Cross-Linguistic Misalignments in Computational Moral Reasoning
by: Farid, Sualeha, et al.
Published: (2025)

Mechanistic Knobs in LLMs: Retrieving and Steering High-Order Semantic Features via Sparse Autoencoders
by: Zhang, Ruikang, et al.
Published: (2026)

SparseRM: A Lightweight Preference Modeling with Sparse Autoencoder
by: Liu, Dengcan, et al.
Published: (2025)

Toward Faithful Retrieval-Augmented Generation with Sparse Autoencoders
by: Xiong, Guangzhi, et al.
Published: (2025)

Sparse Autoencoders for Hypothesis Generation
by: Movva, Rajiv, et al.
Published: (2025)

Steering LLMs? Actually, Sparse Autoencoders can outperform simple baselines
by: Jørgensen, Mikkel Godsk, et al.
Published: (2026)

Democratizing LLMs for Low-Resource Languages by Leveraging their English Dominant Abilities with Linguistically-Diverse Prompts
by: Nguyen, Xuan-Phi, et al.
Published: (2023)

Do LLMs Capture Embodied Cognition and Cultural Variation? Cross-Linguistic Evidence from Demonstratives
by: Wang, Yu, et al.
Published: (2026)

Denoising Concept Vectors with Sparse Autoencoders for Improved Language Model Steering
by: Zhao, Haiyan, et al.
Published: (2025)

SAFER: Probing Safety in Reward Models with Sparse Autoencoder
by: Shi, Wei, et al.
Published: (2025)

Uncovering the Persuasive Fingerprint of LLMs in Jailbreaking Attacks
by: Noughabi, Havva Alizadeh, et al.
Published: (2025)

Show, Don't Tell: Uncovering Implicit Character Portrayal using LLMs
by: Jaipersaud, Brandon, et al.
Published: (2024)

Uncovering the Fragility of Trustworthy LLMs through Chinese Textual Ambiguity
by: Wu, Xinwei, et al.
Published: (2025)

LLMs know their vulnerabilities: Uncover Safety Gaps through Natural Distribution Shifts
by: Ren, Qibing, et al.
Published: (2024)

AxBench: Steering LLMs? Even Simple Baselines Outperform Sparse Autoencoders
by: Wu, Zhengxuan, et al.
Published: (2025)

Parallel Scaling Law: Unveiling Reasoning Generalization through A Cross-Linguistic Perspective
by: Yang, Wen, et al.
Published: (2025)

Popular LLMs Amplify Race and Gender Disparities in Human Mobility
by: Wu, Xinhua, et al.
Published: (2024)

Disentangling concept semantics via multilingual averaging in Sparse Autoencoders
by: O'Reilly, Cliff, et al.
Published: (2025)

A is for Absorption: Studying Feature Splitting and Absorption in Sparse Autoencoders
by: Chanin, David, et al.
Published: (2024)

Controllable LLM Reasoning via Sparse Autoencoder-Based Steering
by: Fang, Yi, et al.
Published: (2026)

SAIF: A Sparse Autoencoder Framework for Interpreting and Steering Instruction Following of Language Models
by: He, Zirui, et al.
Published: (2025)

Sparse Autoencoder Features for Classifications and Transferability
by: Gallifant, Jack, et al.
Published: (2025)

Mapping Clinical Doubt: Locating Linguistic Uncertainty in LLMs
by: Sridhar, Srivarshinee, et al.
Published: (2025)

Large Linguistic Models: Investigating LLMs' metalinguistic abilities
by: Beguš, Gašper, et al.
Published: (2023)

Layer-Wise Perturbations via Sparse Autoencoders for Adversarial Text Generation
by: Shu, Huizhen, et al.
Published: (2025)

Enabling Precise Topic Alignment in Large Language Models Via Sparse Autoencoders
by: Joshi, Ananya, et al.
Published: (2025)

Incorporating Hierarchical Semantics in Sparse Autoencoder Architectures
by: Muchane, Mark, et al.
Published: (2025)

Richer Output for Richer Countries: Uncovering Geographical Disparities in Generated Stories and Travel Recommendations
by: Bhagat, Kirti, et al.
Published: (2024)

How Do LLMs Encode Scientific Quality? An Empirical Study Using Monosemantic Features from Sparse Autoencoders
by: McCoubrey, Michael, et al.
Published: (2026)

SAEMark: Steering Personalized Multilingual LLM Watermarks with Sparse Autoencoders
by: Yu, Zhuohao, et al.
Published: (2025)

Guiding LLM Post-training Data Engineering with Model Internals from Sparse Autoencoders
by: Jing, Yi, et al.
Published: (2026)

Sparse but Wrong: Incorrect L0 Leads to Incorrect Features in Sparse Autoencoders
by: Chanin, David, et al.
Published: (2025)

Palm: A Culturally Inclusive and Linguistically Diverse Dataset for Arabic LLMs
by: Alwajih, Fakhraddin, et al.
Published: (2025)

Uncovering the Potential Risks in Unlearning: Danger of English-only Unlearning in Multilingual LLMs
by: Hwang, Kyomin, et al.
Published: (2025)

LLM Factoscope: Uncovering LLMs' Factual Discernment through Inner States Analysis
by: He, Jinwen, et al.
Published: (2023)

Sparse Neurons Carry Strong Signals of Question Ambiguity in LLMs
by: Zhang, Zhuoxuan, et al.
Published: (2025)

Jacobian Sparse Autoencoders: Sparsify Computations, Not Just Activations
by: Farnik, Lucy, et al.
Published: (2025)

Evaluating Adversarial Robustness of Concept Representations in Sparse Autoencoders
by: Li, Aaron J., et al.
Published: (2025)

Improving Steering Vectors by Targeting Sparse Autoencoder Features
by: Chalnev, Sviatoslav, et al.
Published: (2024)