Imagen de Portada

Compositional Steering of Large Language Models with Steering Tokens

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Radevski, Gorjan, Gashteovski, Kiril, Hong, Giwon, Lawrence, Carolin, Glavaš, Goran
Formato:	Preprint
Publicado:	2026
Materias:	Computation and Language Artificial Intelligence Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

On Synthesizing Data for Context Attribution in Question Answering
por: Radevski, Gorjan, et al.
Publicado: (2025)

Leveraging Open Information Extraction for More Robust Domain Transfer of Event Trigger Detection
por: Dukić, David, et al.
Publicado: (2023)

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

Large Language Models are Miscalibrated In-Context Learners
por: Li, Chengzu, et al.
Publicado: (2023)

COLD-Steer: Steering Large Language Models via In-Context One-step Learning Dynamics
por: Sharma, Kartik, et al.
Publicado: (2026)

FineSteer: A Unified Framework for Fine-Grained Inference-Time Steering in Large Language Models
por: Weng, Zixuan, et al.
Publicado: (2026)

Steering Large Language Models for Machine Translation Personalization
por: Scalena, Daniel, et al.
Publicado: (2025)

Word Embeddings Are Steers for Language Models
por: Han, Chi, et al.
Publicado: (2023)

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

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

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

Dialogue Action Tokens: Steering Language Models in Goal-Directed Dialogue with a Multi-Turn Planner
por: Li, Kenneth, et al.
Publicado: (2024)

HyperSteer: Activation Steering at Scale with Hypernetworks
por: Sun, Jiuding, et al.
Publicado: (2025)

Steer Like the LLM: Activation Steering that Mimics Prompting
por: Heyman, Geert, et al.
Publicado: (2026)

Mitigating Overthinking in Large Reasoning Models via Manifold Steering
por: Huang, Yao, et al.
Publicado: (2025)

Improving Instruction-Following in Language Models through Activation Steering
por: Stolfo, Alessandro, et al.
Publicado: (2024)

Multi-Attribute Steering of Language Models via Targeted Intervention
por: Nguyen, Duy, et al.
Publicado: (2025)

Automating Steering for Safe Multimodal Large Language Models
por: Wu, Lyucheng, et al.
Publicado: (2025)

Linear Representation Transferability Hypothesis: Leveraging Small Models to Steer Large Models
por: Bello, Femi, et al.
Publicado: (2025)

What Drives Representation Steering? A Mechanistic Case Study on Steering Refusal
por: Cheng, Stephen, et al.
Publicado: (2026)

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

ILRR: Inference-Time Steering Method for Masked Diffusion Language Models
por: Avrahami, Eden, et al.
Publicado: (2026)

Beyond Linear Steering: Unified Multi-Attribute Control for Language Models
por: Oozeer, Narmeen, et al.
Publicado: (2025)

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

Steering Large Reasoning Models towards Concise Reasoning via Flow Matching
por: Li, Yawei, et al.
Publicado: (2026)

DAVE: Diagnostic benchmark for Audio Visual Evaluation
por: Radevski, Gorjan, et al.
Publicado: (2025)

Steering Without Breaking: Mechanistically Informed Interventions for Discrete Diffusion Language Models
por: Zhou, Hanhan, et al.
Publicado: (2026)

That's Deprecated! Understanding, Detecting, and Steering Knowledge Conflicts in Language Models for Code Generation
por: Bae, Jaesung, et al.
Publicado: (2025)

MEDDxAgent: A Unified Modular Agent Framework for Explainable Automatic Differential Diagnosis
por: Rose, Daniel, et al.
Publicado: (2025)

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

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

The Information Geometry of Softmax: Probing and Steering
por: Park, Kiho, et al.
Publicado: (2026)

Steering LLMs for Formal Theorem Proving
por: Kirtania, Shashank, et al.
Publicado: (2025)

Programming Refusal with Conditional Activation Steering
por: Lee, Bruce W., et al.
Publicado: (2024)

Steer LLM Latents for Hallucination Detection
por: Park, Seongheon, et al.
Publicado: (2025)

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

UniMaia: Steering Chess Policies with Language for Human-like Play
por: Siu, Sherman, et al.
Publicado: (2026)

Understanding and Steering the Cognitive Behaviors of Reasoning Models at Test-Time
por: Zhang, Zhenyu, et al.
Publicado: (2025)

Do Personality Traits Interfere? Geometric Limitations of Steering in Large Language Models
por: Bhandari, Pranav, et al.
Publicado: (2026)

Learning to Steer: Input-dependent Steering for Multimodal LLMs
por: Parekh, Jayneel, et al.
Publicado: (2025)