Cover Image

Controlling Large Language Models Through Concept Activation Vectors

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zhang, Hanyu, Wang, Xiting, Li, Chengao, Ao, Xiang, He, Qing
Format:	Preprint
Published:	2025
Subjects:	Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Gradient-Adaptive Policy Optimization: Towards Multi-Objective Alignment of Large Language Models
by: Li, Chengao, et al.
Published: (2025)

Uncovering Safety Risks of Large Language Models through Concept Activation Vector
by: Xu, Zhihao, et al.
Published: (2024)

Internal Value Alignment in Large Language Models through Controlled Value Vector Activation
by: Jin, Haoran, et al.
Published: (2025)

Enhancing Safety of Large Language Models via Embedding Space Separation
by: Zhao, Xu, et al.
Published: (2026)

Safe-SAIL: Towards a Fine-grained Safety Landscape of Large Language Models via Sparse Autoencoder Interpretation Framework
by: Weng, Jiaqi, et al.
Published: (2025)

How Large Language Models Need Symbolism
by: Deng, Xiaotie, et al.
Published: (2025)

Controlled Text Generation for Large Language Model with Dynamic Attribute Graphs
by: Liang, Xun, et al.
Published: (2024)

SEAP: Training-free Sparse Expert Activation Pruning Unlock the Brainpower of Large Language Models
by: Liang, Xun, et al.
Published: (2025)

Evaluating Text Creativity across Diverse Domains: A Dataset and Large Language Model Evaluator
by: Cao, Qian, et al.
Published: (2025)

Analogical Reasoning Inside Large Language Models: Concept Vectors and the Limits of Abstraction
by: Opiełka, Gustaw, et al.
Published: (2025)

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

Schrodinger's Memory: Large Language Models
by: Wang, Wei, et al.
Published: (2024)

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

Activation-Space Anchored Access Control for Multi-Class Permission Reasoning in Large Language Models
by: Zhang, Zhaopeng, et al.
Published: (2026)

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

Latent Structure Modulation in Large Language Models Through Stochastic Concept Embedding Transitions
by: Whitaker, Stefan, et al.
Published: (2025)

Knowledge Vector of Logical Reasoning in Large Language Models
by: Wang, Zixuan, et al.
Published: (2026)

Unsupervised Concept Vector Extraction for Bias Control in LLMs
by: Cyberey, Hannah, et al.
Published: (2025)

EmoVerse: Exploring Multimodal Large Language Models for Sentiment and Emotion Understanding
by: Li, Ao, et al.
Published: (2024)

Accounting Reasoning in Large Language Models: Concepts, Evaluation, and Empirical Analysis
by: Zhou, Jie, et al.
Published: (2025)

Locating and Extracting Relational Concepts in Large Language Models
by: Wang, Zijian, et al.
Published: (2024)

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

Measuring Maximum Activations in Open Large Language Models
by: Chen, Luxuan, et al.
Published: (2026)

SLANG: New Concept Comprehension of Large Language Models
by: Mei, Lingrui, et al.
Published: (2024)

Sparse Shift Autoencoders for Identifying Concepts from Large Language Model Activations
by: Joshi, Shruti, et al.
Published: (2025)

AnTKV: Anchor Token-Aware Sub-Bit Vector Quantization for KV Cache in Large Language Models
by: Li, Zeyu, et al.
Published: (2025)

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

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

From Word Vectors to Multimodal Embeddings: Techniques, Applications, and Future Directions For Large Language Models
by: Zhang, Charles, et al.
Published: (2024)

ConceptViz: A Visual Analytics Approach for Exploring Concepts in Large Language Models
by: Li, Haoxuan, et al.
Published: (2025)

ThinkDial: An Open Recipe for Controlling Reasoning Effort in Large Language Models
by: He, Qianyu, et al.
Published: (2025)

Patches of Nonlinearity: Instruction Vectors in Large Language Models
by: Bigoulaeva, Irina, et al.
Published: (2026)

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

Internal Consistency and Self-Feedback in Large Language Models: A Survey
by: Liang, Xun, et al.
Published: (2024)

Activation-Guided Consensus Merging for Large Language Models
by: Yao, Yuxuan, et al.
Published: (2025)

Embracing Anisotropy: Turning Massive Activations into Interpretable Control Knobs for Large Language Models
by: Roh, Youngji, et al.
Published: (2026)

Open-domain Implicit Format Control for Large Language Model Generation
by: Yao, Yiqun, et al.
Published: (2024)

Model Whisper: Steering Vectors Unlock Large Language Models' Potential in Test-time
by: Kang, Xinyue, et al.
Published: (2025)

EFSA: Towards Event-Level Financial Sentiment Analysis
by: Chen, Tianyu, et al.
Published: (2024)

First Activations Matter: Training-Free Methods for Dynamic Activation in Large Language Models
by: Ma, Chi, et al.
Published: (2024)