Imagen de Portada

Semantics-Adaptive Activation Intervention for LLMs via Dynamic Steering Vectors

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Wang, Weixuan, Yang, Jingyuan, Peng, Wei
Formato:	Preprint
Publicado:	2024
Materias:	Computation and Language
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

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

Beyond Steering Vector: Flow-based Activation Steering for Inference-Time Intervention
por: Jin, Zehao, et al.
Publicado: (2026)

ExpertSteer: Intervening in LLMs through Expert Knowledge
por: Wang, Weixuan, et al.
Publicado: (2025)

FairSteer: Inference Time Debiasing for LLMs with Dynamic Activation Steering
por: Li, Yichen, et al.
Publicado: (2025)

Steering MoE LLMs via Expert (De)Activation
por: Fayyaz, Mohsen, et al.
Publicado: (2025)

Prompt-Activation Duality: Improving Activation Steering via Attention-Level Interventions
por: Kang, Diancheng, et al.
Publicado: (2026)

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

Mitigating Memorization in LLMs using Activation Steering
por: Suri, Manan, et al.
Publicado: (2025)

Sharing Matters: Analysing Neurons Across Languages and Tasks in LLMs
por: Wang, Weixuan, et al.
Publicado: (2024)

SALSA: Speech Aware LLM Adaptation via Learned Steering Activation Vectors
por: Yegorova, Yekaterina, et al.
Publicado: (2026)

Steer2Edit: From Activation Steering to Component-Level Editing
por: Sun, Chung-En, et al.
Publicado: (2026)

Towards Reliable Evaluation of Behavior Steering Interventions in LLMs
por: Pres, Itamar, et al.
Publicado: (2024)

Sparse Brains are Also Adaptive Brains: Cognitive-Load-Aware Dynamic Activation for LLMs
por: Yang, Yiheng, et al.
Publicado: (2025)

Understanding How CodeLLMs (Mis)Predict Types with Activation Steering
por: Lucchetti, Francesca, et al.
Publicado: (2024)

Letting Tutor Personas "Speak Up" for LLMs: Learning Steering Vectors from Dialogue via Preference Optimization
por: Lee, Jaewook, et al.
Publicado: (2026)

Mechanistic Knobs in LLMs: Retrieving and Steering High-Order Semantic Features via Sparse Autoencoders
por: Zhang, Ruikang, et al.
Publicado: (2026)

Causal Interventions on Continuous Variables: A Case Study on Verb Bias in Steering Vectors for In-Context Learning
por: Zhou, Zhenghao Herbert, et al.
Publicado: (2026)

Bridging the Language Gaps in Large Language Models with Inference-Time Cross-Lingual Intervention
por: Wang, Weixuan, et al.
Publicado: (2024)

Guiding Giants: Lightweight Controllers for Weighted Activation Steering in LLMs
por: Hegazy, Amr, et al.
Publicado: (2025)

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

Extracting Unlearned Information from LLMs with Activation Steering
por: Seyitoğlu, Atakan, et al.
Publicado: (2024)

Activation-Space Personality Steering: Hybrid Layer Selection for Stable Trait Control in LLMs
por: Bhandari, Pranav, et al.
Publicado: (2025)

Personalized Text Generation with Contrastive Activation Steering
por: Zhang, Jinghao, et al.
Publicado: (2025)

Fine-Grained Activation Steering: Steering Less, Achieving More
por: Feng, Zijian, et al.
Publicado: (2026)

Enhancing Semantic Consistency of Large Language Models through Model Editing: An Interpretability-Oriented Approach
por: Yang, Jingyuan, et al.
Publicado: (2025)

Focus On This, Not That! Steering LLMs with Adaptive Feature Specification
por: Lamb, Tom A., et al.
Publicado: (2024)

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

Activation Steering via Generative Causal Mediation
por: Sankaranarayanan, Aruna, et al.
Publicado: (2026)

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

Activated Parameter Locating via Causal Intervention for Model Merging
por: Kong, Fanshuang, et al.
Publicado: (2024)

Don't Lose Focus: Activation Steering via Key-Orthogonal Projections
por: Luo, Haoyan, et al.
Publicado: (2026)

Steering Awareness: Detecting Activation Steering from Within
por: Rivera, Joshua Fonseca, et al.
Publicado: (2025)

Steering LLMs for Culturally Localized Generation
por: Khanuja, Simran, et al.
Publicado: (2026)

Faithful Bi-Directional Model Steering via Distribution Matching and Distributed Interchange Interventions
por: Bao, Yuntai, et al.
Publicado: (2026)

VSPO: Vector-Steered Policy Optimization for Behavioral Control
por: Zhang, Xuechen, et al.
Publicado: (2026)

Analysing the Safety Pitfalls of Steering Vectors
por: Li, Yuxiao, et al.
Publicado: (2026)

Predicting Where Steering Vectors Succeed
por: Billa, Jayadev
Publicado: (2026)

Infinite Retrieval: Attention Enhanced LLMs in Long-Context Processing
por: Ye, Xiaoju, et al.
Publicado: (2025)

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

Conceptors for Semantic Steering
por: Triantafyllopoulos, Ilias, et al.
Publicado: (2026)