Imagen de Portada

Graph-Regularized Sparse Autoencoders for LLM Safety Steering

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Yeon, Jehyeok, Cinus, Federico, Wu, Yifan, Luceri, Luca
Formato:	Preprint
Publicado:	2025
Materias:	Machine Learning Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Enhancing LLM Steering through Sparse Autoencoder-Based Vector Refinement
por: Wang, Anyi, et al.
Publicado: (2025)

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

Improving Robustness In Sparse Autoencoders via Masked Regularization
por: Narayanaswamy, Vivek, et al.
Publicado: (2026)

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

CorrSteer: Generation-Time LLM Steering via Correlated Sparse Autoencoder Features
por: Cho, Seonglae, et al.
Publicado: (2025)

BarrierSteer: LLM Safety via Learning Barrier Steering
por: Tran, Thanh Q., et al.
Publicado: (2026)

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

Engagement-Driven Content Generation with Large Language Models
por: Coppolillo, Erica, et al.
Publicado: (2024)

The Rogue Scalpel: Activation Steering Compromises LLM Safety
por: Korznikov, Anton, et al.
Publicado: (2025)

IOHunter: Graph Foundation Model to Uncover Online Information Operations
por: Minici, Marco, et al.
Publicado: (2024)

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

Sparse Autoencoders, Again?
por: Lu, Yin, et al.
Publicado: (2025)

Steering LVLMs via Sparse Autoencoder for Hallucination Mitigation
por: Hua, Zhenglin, et al.
Publicado: (2025)

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

Are Sparse Autoencoder Benchmarks Reliable?
por: Chanin, David
Publicado: (2026)

BatchTopK Sparse Autoencoders
por: Bussmann, Bart, et al.
Publicado: (2024)

Improving Sparse Autoencoder with Dynamic Attention
por: Wang, Dongsheng, et al.
Publicado: (2026)

Are Sparse Autoencoders Useful? A Case Study in Sparse Probing
por: Kantamneni, Subhash, et al.
Publicado: (2025)

Adaptive Sparse Allocation with Mutual Choice & Feature Choice Sparse Autoencoders
por: Ayonrinde, Kola
Publicado: (2024)

Empirical Evaluation of Progressive Coding for Sparse Autoencoders
por: Peter, Hans, et al.
Publicado: (2025)

On the transferability of Sparse Autoencoders for interpreting compressed models
por: Gupte, Suchit, et al.
Publicado: (2025)

Data Whitening Improves Sparse Autoencoder Learning
por: Saraswatula, Ashwin, et al.
Publicado: (2025)

Do Sparse Autoencoders Capture Concept Manifolds?
por: Bhalla, Usha, et al.
Publicado: (2026)

Improving Dictionary Learning with Gated Sparse Autoencoders
por: Rajamanoharan, Senthooran, et al.
Publicado: (2024)

CREMA: A Contrastive Regularized Masked Autoencoder for Robust ECG Diagnostics across Clinical Domains
por: Song, Junho, et al.
Publicado: (2024)

SteeringSafety: A Systematic Safety Evaluation Framework of Representation Steering in LLMs
por: Siu, Vincent, et al.
Publicado: (2025)

Steering Large Language Model Activations in Sparse Spaces
por: Bayat, Reza, et al.
Publicado: (2025)

Beyond Interpretability: When, Why, and How Sparse Autoencoders Enable Label-Free Visual Steering
por: Chatzoudis, Gerasimos, et al.
Publicado: (2025)

Steering Sparse Autoencoder Latents to Control Dynamic Head Pruning in Vision Transformers (Student Abstract)
por: Lee, Yousung, et al.
Publicado: (2026)

Revisiting Graph Autoencoders as Implicit Contrastive Learners
por: Li, Jintang, et al.
Publicado: (2024)

Learning Multi-Level Features with Matryoshka Sparse Autoencoders
por: Bussmann, Bart, et al.
Publicado: (2025)

Sparse Autoencoders Do Not Find Canonical Units of Analysis
por: Leask, Patrick, et al.
Publicado: (2025)

Evaluating and Designing Sparse Autoencoders by Approximating Quasi-Orthogonality
por: Lee, Sewoong, et al.
Publicado: (2025)

Revis: Sparse Latent Steering to Mitigate Object Hallucination in Large Vision-Language Models
por: Wu, Jialin, et al.
Publicado: (2026)

Steered LLM Activations are Non-Surjective
por: Mishra, Aayush, et al.
Publicado: (2026)

Graph Autoencoder for Process Monitoring
por: Zhang, Xiangrui
Publicado: (2026)

AgentKit: Structured LLM Reasoning with Dynamic Graphs
por: Wu, Yue, et al.
Publicado: (2024)

BikeVAE-GNN: A Variational Autoencoder-Augmented Hybrid Graph Neural Network for Sparse Bicycle Volume Estimation
por: Gupta, Mohit, et al.
Publicado: (2025)

Beyond Redundancy: Diverse and Specialized Multi-Expert Sparse Autoencoder
por: Xu, Zhen, et al.
Publicado: (2025)

Projecting Assumptions: The Duality Between Sparse Autoencoders and Concept Geometry
por: Hindupur, Sai Sumedh R., et al.
Publicado: (2025)