Copertina

Steering Large Language Model Activations in Sparse Spaces

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Bayat, Reza, Rahimi-Kalahroudi, Ali, Pezeshki, Mohammad, Chandar, Sarath, Vincent, Pascal
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Machine Learning Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

The Pitfalls of Memorization: When Memorization Hurts Generalization
di: Bayat, Reza, et al.
Pubblicazione: (2024)

Partial Models for Building Adaptive Model-Based Reinforcement Learning Agents
di: Alver, Safa, et al.
Pubblicazione: (2024)

Are self-explanations from Large Language Models faithful?
di: Madsen, Andreas, et al.
Pubblicazione: (2024)

Context-Aware Assistant Selection for Improved Inference Acceleration with Large Language Models
di: Huang, Jerry, et al.
Pubblicazione: (2024)

Effect of Document Packing on the Latent Multi-Hop Reasoning Capabilities of Large Language Models
di: Prato, Gabriele, et al.
Pubblicazione: (2025)

Too Big to Fool: Resisting Deception in Language Models
di: Samsami, Mohammad Reza, et al.
Pubblicazione: (2024)

Do Large Language Models Know How Much They Know?
di: Prato, Gabriele, et al.
Pubblicazione: (2025)

Shielded Controller Units for RL with Operational Constraints Applied to Remote Microgrids
di: Nekoei, Hadi, et al.
Pubblicazione: (2025)

Compositional Risk Minimization
di: Mahajan, Divyat, et al.
Pubblicazione: (2024)

Neural Coherence : Find higher performance to out-of-distribution tasks from few samples
di: Guiroy, Simon, et al.
Pubblicazione: (2025)

Intelligent Switching for Reset-Free RL
di: Patil, Darshan, et al.
Pubblicazione: (2024)

Lookbehind-SAM: k steps back, 1 step forward
di: Mordido, Gonçalo, et al.
Pubblicazione: (2023)

Amnesia: Adversarial Semantic Layer Specific Activation Steering in Large Language Models
di: Raza, Ali, et al.
Pubblicazione: (2026)

Discovering environments with XRM
di: Pezeshki, Mohammad, et al.
Pubblicazione: (2023)

Squeezing More from the Stream : Learning Representation Online for Streaming Reinforcement Learning
di: Nilaksh, et al.
Pubblicazione: (2026)

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

GRPO-$λ$: Credit Assignment improves LLM Reasoning
di: Parthasarathi, Prasanna, et al.
Pubblicazione: (2025)

Towards Practical Tool Usage for Continually Learning LLMs
di: Huang, Jerry, et al.
Pubblicazione: (2024)

Revisiting Replay and Gradient Alignment for Continual Pre-Training of Large Language Models
di: Abbes, Istabrak, et al.
Pubblicazione: (2025)

MLLMEraser: Achieving Test-Time Unlearning in Multimodal Large Language Models through Activation Steering
di: Ding, Chenlu, et al.
Pubblicazione: (2025)

Interpretable Steering of Large Language Models with Feature Guided Activation Additions
di: Soo, Samuel, et al.
Pubblicazione: (2025)

Multi-property Steering of Large Language Models with Dynamic Activation Composition
di: Scalena, Daniel, et al.
Pubblicazione: (2024)

ContextFocus: Activation Steering for Contextual Faithfulness in Large Language Models
di: Anand, Nikhil, et al.
Pubblicazione: (2026)

Torque-Aware Momentum
di: Malviya, Pranshu, et al.
Pubblicazione: (2024)

Performance Control in Early Exiting to Deploy Large Models at the Same Cost of Smaller Ones
di: Mofakhami, Mehrnaz, et al.
Pubblicazione: (2024)

Structured Sparse Transition Matrices to Enable State Tracking in State-Space Models
di: Terzić, Aleksandar, et al.
Pubblicazione: (2025)

Angular Steering: Behavior Control via Rotation in Activation Space
di: Vu, Hieu M., et al.
Pubblicazione: (2025)

Endogenous Resistance to Activation Steering in Language Models
di: McKenzie, Alex, et al.
Pubblicazione: (2026)

SAKE: Steering Activations for Knowledge Editing
di: Scialanga, Marco, et al.
Pubblicazione: (2025)

Promoting Exploration in Memory-Augmented Adam using Critical Momenta
di: Malviya, Pranshu, et al.
Pubblicazione: (2023)

Flash PD-SSM: Memory-Optimized Structured Sparse State-Space Models
di: Terzić, Aleksandar, et al.
Pubblicazione: (2026)

Why Don't Prompt-Based Fairness Metrics Correlate?
di: Zayed, Abdelrahman, et al.
Pubblicazione: (2024)

Should We Attend More or Less? Modulating Attention for Fairness
di: Zayed, Abdelrahman, et al.
Pubblicazione: (2023)

Compositional Steering of Large Language Models with Steering Tokens
di: Radevski, Gorjan, et al.
Pubblicazione: (2026)

Do Robot Snakes Dream like Electric Sheep? Investigating the Effects of Architectural Inductive Biases on Hallucination
di: Huang, Jerry, et al.
Pubblicazione: (2024)

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

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

Iterative Amortized Inference: Unifying In-Context Learning and Learned Optimizers
di: Mittal, Sarthak, et al.
Pubblicazione: (2025)

Dynamically Scaled Activation Steering
di: Ferrando, Alex, et al.
Pubblicazione: (2025)

Uncertainty-Aware Generative Oversampling Using an Entropy-Guided Conditional Variational Autoencoder
di: Zare, Amirhossein, et al.
Pubblicazione: (2025)