Imagen de Portada

Dialz: A Python Toolkit for Steering Vectors

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Siddique, Zara, Turner, Liam D., Espinosa-Anke, Luis
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

Shifting Perspectives: Steering Vectors for Robust Bias Mitigation in LLMs
por: Siddique, Zara, et al.
Publicado: (2025)

CHEW: A Dataset of CHanging Events in Wikipedia
por: Borkakoty, Hsuvas, et al.
Publicado: (2024)

Hoaxpedia: A Unified Wikipedia Hoax Articles Dataset
por: Borkakoty, Hsuvas, et al.
Publicado: (2024)

On the Non-Identifiability of Steering Vectors in Large Language Models
por: Venkatesh, Sohan, et al.
Publicado: (2026)

Understanding Reasoning in Thinking Language Models via Steering Vectors
por: Venhoff, Constantin, et al.
Publicado: (2025)

libcll: an Extendable Python Toolkit for Complementary-Label Learning
por: Ye, Nai-Xuan, et al.
Publicado: (2024)

Who is better at math, Jenny or Jingzhen? Uncovering Stereotypes in Large Language Models
por: Siddique, Zara, et al.
Publicado: (2024)

Review of Digital Asset Development with Graph Neural Network Unlearning
por: Lisbon, Zara
Publicado: (2024)

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

LangFIR: Discovering Sparse Language-Specific Features from Monolingual Data for Language Steering
por: Wong, Sing Hieng, et al.
Publicado: (2026)

One-shot Optimized Steering Vectors Mediate Safety-relevant Behaviors in LLMs
por: Dunefsky, Jacob, et al.
Publicado: (2025)

SDialog: A Python Toolkit for End-to-End Agent Building, User Simulation, Dialog Generation, and Evaluation
por: Burdisso, Sergio, et al.
Publicado: (2025)

Steer2Adapt: Dynamically Composing Steering Vectors Elicits Efficient Adaptation of LLMs
por: Han, Pengrui, et al.
Publicado: (2026)

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

AdvSecureNet: A Python Toolkit for Adversarial Machine Learning
por: Catal, Melih, et al.
Publicado: (2024)

DetoxAI: a Python Toolkit for Debiasing Deep Learning Models in Computer Vision
por: Stępka, Ignacy, et al.
Publicado: (2025)

Steering Llama 2 via Contrastive Activation Addition
por: Panickssery, Nina, et al.
Publicado: (2023)

To Steer or Not to Steer? Mechanistic Error Reduction with Abstention for Language Models
por: Hedström, Anna, et al.
Publicado: (2025)

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

MidSteer: Optimal Affine Framework for Steering Generative Models
por: Gaintseva, Tatiana, et al.
Publicado: (2026)

Understanding Unreliability of Steering Vectors in Language Models: Geometric Predictors and the Limits of Linear Approximations
por: Braun, Joschka
Publicado: (2026)

Awesome-OL: An Extensible Toolkit for Online Learning
por: Liu, Zeyi, et al.
Publicado: (2025)

Interpretable Embeddings with Sparse Autoencoders: A Data Analysis Toolkit
por: Jiang, Nick, et al.
Publicado: (2025)

PyG-SSL: A Graph Self-Supervised Learning Toolkit
por: Zheng, Lecheng, et al.
Publicado: (2024)

FlexMol: A Flexible Toolkit for Benchmarking Molecular Relational Learning
por: Liu, Sizhe, et al.
Publicado: (2024)

In-context Vectors: Making In Context Learning More Effective and Controllable Through Latent Space Steering
por: Liu, Sheng, et al.
Publicado: (2023)

DreamReader: An Interpretability Toolkit for Text-to-Image Models
por: Prakash, Nirmalendu, et al.
Publicado: (2026)

Global Evolutionary Steering: Refining Activation Steering Control via Cross-Layer Consistency
por: Jiang, Xinyan, et al.
Publicado: (2026)

FMTK: A Modular Toolkit for Composable Time Series Foundation Model Pipelines
por: Shastri, Hetvi, et al.
Publicado: (2025)

Imitation Learning Datasets: A Toolkit For Creating Datasets, Training Agents and Benchmarking
por: Gavenski, Nathan, et al.
Publicado: (2024)

Quanda: An Interpretability Toolkit for Training Data Attribution Evaluation and Beyond
por: Bareeva, Dilyara, et al.
Publicado: (2024)

Dynamically Scaled Activation Steering
por: Ferrando, Alex, et al.
Publicado: (2025)

UncertaintyZoo: A Unified Toolkit for Quantifying Predictive Uncertainty in Deep Learning Systems
por: Wu, Xianzong, et al.
Publicado: (2025)

GREATERPROMPT: A Unified, Customizable, and High-Performing Open-Source Toolkit for Prompt Optimization
por: Zheng, Wenliang, et al.
Publicado: (2025)

SafeTuneBed: A Toolkit for Benchmarking LLM Safety Alignment in Fine-Tuning
por: Hossain, Saad, et al.
Publicado: (2025)

On Optimal Steering to Achieve Exact Fairness
por: Sharma, Mohit, et al.
Publicado: (2025)

Activation Steering for Chain-of-Thought Compression
por: Azizi, Seyedarmin, et al.
Publicado: (2025)

Minimizing Collateral Damage in Activation Steering
por: Nguyen, Tam, et al.
Publicado: (2026)

Concept Heterogeneity-aware Representation Steering
por: Abdullaev, Laziz U., et al.
Publicado: (2026)

General and Efficient Steering of Unconditional Diffusion
por: Wang, Qingsong, et al.
Publicado: (2026)