Cover Image

Mitigating the Safety-utility Trade-off in LLM Alignment via Adaptive Safe Context Learning

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Wang, Yanbo, Wang, Minzheng, Liang, Jian, Wang, Lu, Yu, Yongcan, He, Ran
Format:	Preprint
Published:	2026
Subjects:	Cryptography and Security Artificial Intelligence Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Test-Time Immunization: A Universal Defense Framework Against Jailbreaks for (Multimodal) Large Language Models
by: Yu, Yongcan, et al.
Published: (2025)

A Comprehensive Survey on Trustworthiness in Reasoning with Large Language Models
by: Wang, Yanbo, et al.
Published: (2025)

Do We Really Need Curated Malicious Data for Safety Alignment in Multi-modal Large Language Models?
by: Wang, Yanbo, et al.
Published: (2025)

SafeAligner: Safety Alignment against Jailbreak Attacks via Response Disparity Guidance
by: Huang, Caishuang, et al.
Published: (2024)

Mitigating Fine-tuning based Jailbreak Attack with Backdoor Enhanced Safety Alignment
by: Wang, Jiongxiao, et al.
Published: (2024)

Understanding and Mitigating Over-refusal for Large Language Models via Safety Representation
by: Zhang, Junbo, et al.
Published: (2025)

TWGuard: A Case Study of LLM Safety Guardrails for Localized Linguistic Contexts
by: Chu, Hua-Rong, et al.
Published: (2026)

Be Your Own Red Teamer: Safety Alignment via Self-Play and Reflective Experience Replay
by: Wang, Hao, et al.
Published: (2026)

WaterPool: A Watermark Mitigating Trade-offs among Imperceptibility, Efficacy and Robustness
by: Huang, Baizhou, et al.
Published: (2024)

Context Misleads LLMs: The Role of Context Filtering in Maintaining Safe Alignment of LLMs
by: Kim, Jinhwa, et al.
Published: (2025)

SciSafeEval: A Comprehensive Benchmark for Safety Alignment of Large Language Models in Scientific Tasks
by: Li, Tianhao, et al.
Published: (2024)

From Trade-off to Synergy: A Versatile Symbiotic Watermarking Framework for Large Language Models
by: Wang, Yidan, et al.
Published: (2025)

Towards Eliminating Hard Label Constraints in Gradient Inversion Attacks
by: Wang, Yanbo, et al.
Published: (2024)

GuidedBench: Measuring and Mitigating the Evaluation Discrepancies of In-the-wild LLM Jailbreak Methods
by: Huang, Ruixuan, et al.
Published: (2025)

Disabling Self-Correction in Retrieval-Augmented Generation via Stealthy Retriever Poisoning
by: Dai, Yanbo, et al.
Published: (2025)

Invisible Entropy: Towards Safe and Efficient Low-Entropy LLM Watermarking
by: Gu, Tianle, et al.
Published: (2025)

Do Prompts Guarantee Safety? Mitigating Toxicity from LLM Generations through Subspace Intervention
by: Singh, Himanshu, et al.
Published: (2026)

GradSafe: Detecting Jailbreak Prompts for LLMs via Safety-Critical Gradient Analysis
by: Xie, Yueqi, et al.
Published: (2024)

EnchTable: Unified Safety Alignment Transfer in Fine-tuned Large Language Models
by: Wu, Jialin, et al.
Published: (2025)

PandaGuard: Systematic Evaluation of LLM Safety against Jailbreaking Attacks
by: Shen, Guobin, et al.
Published: (2025)

Safely Learning with Private Data: A Federated Learning Framework for Large Language Model
by: Zheng, JiaYing, et al.
Published: (2024)

No Free Lunch in LLM Watermarking: Trade-offs in Watermarking Design Choices
by: Pang, Qi, et al.
Published: (2024)

Improving LLM Safety Alignment with Dual-Objective Optimization
by: Zhao, Xuandong, et al.
Published: (2025)

Beyond Jailbreaks: Revealing Stealthier and Broader LLM Security Risks Stemming from Alignment Failures
by: Zhou, Yukai, et al.
Published: (2025)

SEA: Low-Resource Safety Alignment for Multimodal Large Language Models via Synthetic Embeddings
by: Lu, Weikai, et al.
Published: (2025)

Interpretable LLM Guardrails via Sparse Representation Steering
by: He, Zeqing, et al.
Published: (2025)

SafeKey: Amplifying Aha-Moment Insights for Safety Reasoning
by: Zhou, Kaiwen, et al.
Published: (2025)

Constraint-Level Design of zkEVMs: Architectures, Trade-offs, and Evolution
by: Hassanzadeh-Nazarabadi, Yahya, et al.
Published: (2025)

PRISM: Privacy-Aware Routing for Adaptive Cloud-Edge LLM Inference via Semantic Sketch Collaboration
by: Zhan, Junfei, et al.
Published: (2025)

ContextLeak: Auditing Leakage in Private In-Context Learning Methods
by: Choi, Jacob, et al.
Published: (2025)

What Matters For Safety Alignment?
by: Li, Xing, et al.
Published: (2026)

LLM Reinforcement in Context
by: Rivasseau, Thomas
Published: (2025)

Universal and Context-Independent Triggers for Precise Control of LLM Outputs
by: Liang, Jiashuo, et al.
Published: (2024)

Root Defence Strategies: Ensuring Safety of LLM at the Decoding Level
by: Zeng, Xinyi, et al.
Published: (2024)

When Safety Becomes a Vulnerability: Exploiting LLM Alignment Homogeneity for Transferable Blocking in RAG
by: Li, Junchen, et al.
Published: (2026)

Synthetic Data for Veterinary EHR De-identification: Benefits, Limits, and Safety Trade-offs Under Fixed Compute
by: Brundage, David
Published: (2026)

Lifelong Safety Alignment for Language Models
by: Wang, Haoyu, et al.
Published: (2025)

Stop Tracking Me! Proactive Defense Against Attribute Inference Attack in LLMs
by: Yan, Dong, et al.
Published: (2026)

Federated In-Context LLM Agent Learning
by: Wu, Panlong, 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)