Imagen de Portada

Model Whisper: Steering Vectors Unlock Large Language Models' Potential in Test-time

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Kang, Xinyue, Shi, Diwei, Chen, Li
Formato:	Preprint
Publicado:	2025
Materias:	Computation and Language
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Style Vectors for Steering Generative Large Language Model
por: Konen, Kai, et al.
Publicado: (2024)

Steering Vector Fields for Context-Aware Inference-Time Control in Large Language Models
por: Li, Jiaqian, et al.
Publicado: (2026)

Personalized Steering of Large Language Models: Versatile Steering Vectors Through Bi-directional Preference Optimization
por: Cao, Yuanpu, et al.
Publicado: (2024)

Unlocking the Potential: Benchmarking Large Language Models in Water Engineering and Research
por: Xu, Boyan, et al.
Publicado: (2024)

The Impact of Steering Large Language Models with Persona Vectors in Educational Applications
por: Wu, Yongchao, et al.
Publicado: (2026)

Youtu-LLM: Unlocking the Native Agentic Potential for Lightweight Large Language Models
por: Lu, Junru, et al.
Publicado: (2025)

Whispers that Shake Foundations: Analyzing and Mitigating False Premise Hallucinations in Large Language Models
por: Yuan, Hongbang, et al.
Publicado: (2024)

BILLY: Steering Large Language Models via Merging Persona Vectors for Creative Generation
por: Pai, Tsung-Min, et al.
Publicado: (2025)

Unlocking the Potential of Large Language Models in the Nuclear Industry with Synthetic Data
por: Anwar, Muhammad, et al.
Publicado: (2025)

The Effectiveness of Style Vectors for Steering Large Language Models: A Human Evaluation
por: Diallo, Diaoulé, et al.
Publicado: (2026)

Learning to Compress: Unlocking the Potential of Large Language Models for Text Representation
por: Zhang, Yeqin, et al.
Publicado: (2025)

Psychological Steering of Large Language Models
por: Blas, Leonardo, et al.
Publicado: (2026)

Prototype-Based Dynamic Steering for Large Language Models
por: Kayan, Ceyhun Efe, et al.
Publicado: (2025)

Decomposing and Steering Functional Metacognition in Large Language Models
por: Li, Yanshi, et al.
Publicado: (2026)

RepIt: Steering Language Models with Concept-Specific Refusal Vectors
por: Siu, Vincent, et al.
Publicado: (2025)

Unlocking the Power of Large Language Models for Entity Alignment
por: Jiang, Xuhui, et al.
Publicado: (2024)

Textual Steering Vectors Can Improve Visual Understanding in Multimodal Large Language Models
por: Gan, Woody Haosheng, et al.
Publicado: (2025)

Unlocking the Future: Exploring Look-Ahead Planning Mechanistic Interpretability in Large Language Models
por: Men, Tianyi, et al.
Publicado: (2024)

Unlocking the Potential of Model Merging for Low-Resource Languages
por: Tao, Mingxu, et al.
Publicado: (2024)

LF-Steering: Latent Feature Activation Steering for Enhancing Semantic Consistency in Large Language Models
por: Yang, Jingyuan, et al.
Publicado: (2025)

Unlocking the Potentials of Retrieval-Augmented Generation for Diffusion Language Models
por: Yu, Chuanyue, et al.
Publicado: (2026)

Evaluating and Steering Modality Preferences in Multimodal Large Language Model
por: Zhang, Yu, et al.
Publicado: (2025)

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

Skills-in-Context Prompting: Unlocking Compositionality in Large Language Models
por: Chen, Jiaao, et al.
Publicado: (2023)

Adaptive Task Vectors for Large Language Models
por: Kang, Joonseong, et al.
Publicado: (2025)

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

Sorted LLaMA: Unlocking the Potential of Intermediate Layers of Large Language Models for Dynamic Inference
por: Kavehzadeh, Parsa, et al.
Publicado: (2023)

Mechanistic Indicators of Steering Effectiveness in Large Language Models
por: Jafari, Mehdi, et al.
Publicado: (2026)

Safety Arithmetic: A Framework for Test-time Safety Alignment of Language Models by Steering Parameters and Activations
por: Hazra, Rima, et al.
Publicado: (2024)

Steering Large Language Models between Code Execution and Textual Reasoning
por: Chen, Yongchao, et al.
Publicado: (2024)

Steering When Necessary: Flexible Steering Large Language Models with Backtracking
por: Cheng, Zifeng, et al.
Publicado: (2025)

Beyond Static Personas: Situational Personality Steering for Large Language Models
por: Wei, Zesheng, et al.
Publicado: (2026)

Towards Inference-time Category-wise Safety Steering for Large Language Models
por: Bhattacharjee, Amrita, et al.
Publicado: (2024)

CoSToM:Causal-oriented Steering for Intrinsic Theory-of-Mind Alignment in Large Language Models
por: Li, Mengfan, et al.
Publicado: (2026)

RIRO: Reshaping Inputs, Refining Outputs Unlocking the Potential of Large Language Models in Data-Scarce Contexts
por: Hamdi, Ali, et al.
Publicado: (2024)

Function Vectors in Large Language Models
por: Todd, Eric, et al.
Publicado: (2023)

Merlin's Whisper: Enabling Efficient Reasoning in Large Language Models via Black-box Persuasive Prompting
por: Xia, Heming, et al.
Publicado: (2025)

Multilingual Political Views of Large Language Models: Identification and Steering
por: Gurgurov, Daniil, et al.
Publicado: (2025)

Controlling Large Language Model Agents with Entropic Activation Steering
por: Rahn, Nate, et al.
Publicado: (2024)

Evaluating Large Language Model Biases in Persona-Steered Generation
por: Liu, Andy, et al.
Publicado: (2024)