Cover Image

Internal Value Alignment in Large Language Models through Controlled Value Vector Activation

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Jin, Haoran, Li, Meng, Wang, Xiting, Xu, Zhihao, Huang, Minlie, Jia, Yantao, Lian, Defu
Format:	Preprint
Published:	2025
Subjects:	Computation and Language Artificial Intelligence Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

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

Benchmarking Multi-National Value Alignment for Large Language Models
by: Shi, Weijie, et al.
Published: (2025)

Understanding Privacy Risks of Embeddings Induced by Large Language Models
by: Zhu, Zhihao, et al.
Published: (2024)

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

Don't Forget Your Reward Values: Language Model Alignment via Value-based Calibration
by: Mao, Xin, et al.
Published: (2024)

Evaluating Readability and Faithfulness of Concept-based Explanations
by: Li, Meng, et al.
Published: (2024)

Trojan Activation Attack: Red-Teaming Large Language Models using Activation Steering for Safety-Alignment
by: Wang, Haoran, et al.
Published: (2023)

Diverse Human Value Alignment for Large Language Models via Ethical Reasoning
by: Wang, Jiahao, et al.
Published: (2025)

VALUEFLOW: Toward Pluralistic and Steerable Value-based Alignment in Large Language Models
by: Kim, Woojin, et al.
Published: (2026)

Measuring Human and AI Values Based on Generative Psychometrics with Large Language Models
by: Ye, Haoran, et al.
Published: (2024)

MiniLLM: On-Policy Distillation of Large Language Models
by: Gu, Yuxian, et al.
Published: (2023)

Generative Psycho-Lexical Approach for Constructing Value Systems in Large Language Models
by: Ye, Haoran, et al.
Published: (2025)

Beyond Human Norms: Unveiling Unique Values of Large Language Models through Interdisciplinary Approaches
by: Biedma, Pablo, et al.
Published: (2024)

Heterogeneous Value Alignment Evaluation for Large Language Models
by: Zhang, Zhaowei, et al.
Published: (2023)

Understanding the Dilemma of Unlearning for Large Language Models
by: Zhang, Qingjie, et al.
Published: (2025)

Inference-Time Language Model Alignment via Integrated Value Guidance
by: Liu, Zhixuan, et al.
Published: (2024)

Perception of Knowledge Boundary for Large Language Models through Semi-open-ended Question Answering
by: Wen, Zhihua, et al.
Published: (2024)

Value Augmented Sampling for Language Model Alignment and Personalization
by: Han, Seungwook, et al.
Published: (2024)

UniMEL: A Unified Framework for Multimodal Entity Linking with Large Language Models
by: Qi, Liu, et al.
Published: (2024)

VISPA: Pluralistic Alignment via Automatic Value Selection and Activation
by: Zheng, Shenyan, et al.
Published: (2026)

Efficient and Stable Reinforcement Learning for Diffusion Language Models
by: Liu, Jiawei, et al.
Published: (2026)

Confabulation: The Surprising Value of Large Language Model Hallucinations
by: Sui, Peiqi, et al.
Published: (2024)

Prompt-Based Value Steering of Large Language Models
by: Abbo, Giulio Antonio, et al.
Published: (2025)

VAL-Bench: Belief Consistency as a measure for Value Alignment in Language Models
by: Gupta, Aman, et al.
Published: (2025)

LocalValueBench: A Collaboratively Built and Extensible Benchmark for Evaluating Localized Value Alignment and Ethical Safety in Large Language Models
by: Meadows, Gwenyth Isobel, et al.
Published: (2024)

Refine Large Language Model Fine-tuning via Instruction Vector
by: Jiang, Gangwei, et al.
Published: (2024)

Model Extrapolation Expedites Alignment
by: Zheng, Chujie, et al.
Published: (2024)

HAVE: Head-Adaptive Gating and ValuE Calibration for Hallucination Mitigation in Large Language Models
by: Tong, Xin, et al.
Published: (2025)

Flames: Benchmarking Value Alignment of LLMs in Chinese
by: Huang, Kexin, et al.
Published: (2023)

Language Models Are Capable of Metacognitive Monitoring and Control of Their Internal Activations
by: Ji-An, Li, et al.
Published: (2025)

Are Large Language Models Consistent over Value-laden Questions?
by: Moore, Jared, et al.
Published: (2024)

High-Dimension Human Value Representation in Large Language Models
by: Cahyawijaya, Samuel, et al.
Published: (2024)

Relative Value Biases in Large Language Models
by: Hayes, William M., et al.
Published: (2024)

Defending against Jailbreak through Early Exit Generation of Large Language Models
by: Zhao, Chongwen, et al.
Published: (2024)

VC-Soup: Value-Consistency Guided Multi-Value Alignment for Large Language Models
by: Xu, Hefei, et al.
Published: (2026)

Value-Conflict Diagnostics Reveal Widespread Alignment Faking in Language Models
by: Nair, Inderjeet, et al.
Published: (2026)

Distributive Fairness in Large Language Models: Evaluating Alignment with Human Values
by: Hosseini, Hadi, et al.
Published: (2025)

AlignBench: Benchmarking Chinese Alignment of Large Language Models
by: Liu, Xiao, et al.
Published: (2023)

MEUV: Achieving Fine-Grained Capability Activation in Large Language Models via Mutually Exclusive Unlock Vectors
by: Tong, Xin, et al.
Published: (2025)

On Prompt-Driven Safeguarding for Large Language Models
by: Zheng, Chujie, et al.
Published: (2024)