Cover Image

Understanding and Mitigating Over-refusal for Large Language Models via Safety Representation

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zhang, Junbo, Chen, Ran, Zhou, Qianli, Deng, Xinyang, Jiang, Wen
Format:	Preprint
Published:	2025
Subjects:	Cryptography and Security Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

DataShield: Safety-degrading Data Filtering for LLM Benign Instruction Fine-Tuning
by: Zhang, Junbo, et al.
Published: (2026)

Jailbreak Antidote: Runtime Safety-Utility Balance via Sparse Representation Adjustment in Large Language Models
by: Shen, Guobin, et al.
Published: (2024)

Representation Bending for Large Language Model Safety
by: Yousefpour, Ashkan, et al.
Published: (2025)

ML-Bench&Guard: Policy-Grounded Multilingual Safety Benchmark and Guardrail for Large Language Models
by: Zhao, Yunhan, et al.
Published: (2026)

S-Eval: Towards Automated and Comprehensive Safety Evaluation for Large Language Models
by: Yuan, Xiaohan, et al.
Published: (2024)

Jailbreaking Leaves a Trace: Understanding and Detecting Jailbreak Attacks from Internal Representations of Large Language Models
by: Kadali, Sri Durga Sai Sowmya, et al.
Published: (2026)

Robust LLM safeguarding via refusal feature adversarial training
by: Yu, Lei, et al.
Published: (2024)

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

Don't Listen To Me: Understanding and Exploring Jailbreak Prompts of Large Language Models
by: Yu, Zhiyuan, et al.
Published: (2024)

One Trigger Token Is Enough: A Defense Strategy for Balancing Safety and Usability in Large Language Models
by: Gu, Haoran, et al.
Published: (2025)

REEF: Representation Encoding Fingerprints for Large Language Models
by: Zhang, Jie, et al.
Published: (2024)

GoldCoin: Grounding Large Language Models in Privacy Laws via Contextual Integrity Theory
by: Fan, Wei, et al.
Published: (2024)

Mitigating the Safety-utility Trade-off in LLM Alignment via Adaptive Safe Context Learning
by: Wang, Yanbo, et al.
Published: (2026)

BadApex: Backdoor Attack Based on Adaptive Optimization Mechanism of Black-box Large Language Models
by: Wu, Zhengxian, et al.
Published: (2025)

Sanitize Your Responses: Mitigating Privacy Leakage in Large Language Models
by: Fu, Wenjie, et al.
Published: (2025)

Internal Safety Collapse in Frontier Large Language Models
by: Wu, Yutao, et al.
Published: (2026)

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

Resource Consumption Red-Teaming for Large Vision-Language Models
by: Gao, Haoran, et al.
Published: (2025)

AgentAlign: Navigating Safety Alignment in the Shift from Informative to Agentic Large Language Models
by: Zhang, Jinchuan, et al.
Published: (2025)

BadLingual: A Novel Lingual-Backdoor Attack against Large Language Models
by: Wang, Zihan, et al.
Published: (2025)

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

ConfGuard: A Simple and Effective Backdoor Detection for Large Language Models
by: Wang, Zihan, et al.
Published: (2025)

Character as a Latent Variable in Large Language Models: A Mechanistic Account of Emergent Misalignment and Conditional Safety Failures
by: Su, Yanghao, et al.
Published: (2026)

Prompt Stealing Attacks Against Large Language Models
by: Sha, Zeyang, et al.
Published: (2024)

Yet Another Watermark for Large Language Models
by: Bao, Siyuan, et al.
Published: (2025)

SGuard-v1: Safety Guardrail for Large Language Models
by: Lee, JoonHo, et al.
Published: (2025)

Learning-Based Automated Adversarial Red-Teaming for Robustness Evaluation of Large Language Models
by: Wei, Zhang, et al.
Published: (2025)

MBTSAD: Mitigating Backdoors in Language Models Based on Token Splitting and Attention Distillation
by: Ding, Yidong, et al.
Published: (2025)

Watermarking Large Language Models and the Generated Content: Opportunities and Challenges
by: Zhang, Ruisi, et al.
Published: (2024)

Model-Agnostic Lifelong LLM Safety via Externalized Attack-Defense Co-Evolution
by: Zhang, Xiaozhe, et al.
Published: (2026)

Majority Bit-Aware Watermarking For Large Language Models
by: Xu, Jiahao, et al.
Published: (2025)

HLPD: Aligning LLMs to Human Language Preference for Machine-Revised Text Detection
by: Dai, Fangqi, et al.
Published: (2025)

On the Role of Attention Heads in Large Language Model Safety
by: Zhou, Zhenhong, et al.
Published: (2024)

InjecGuard: Benchmarking and Mitigating Over-defense in Prompt Injection Guardrail Models
by: Li, Hao, et al.
Published: (2024)

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

Privacy in Large Language Models: Attacks, Defenses and Future Directions
by: Li, Haoran, et al.
Published: (2023)

Separator Injection Attack: Uncovering Dialogue Biases in Large Language Models Caused by Role Separators
by: Li, Xitao, et al.
Published: (2025)

MLLMGuard: A Multi-dimensional Safety Evaluation Suite for Multimodal Large Language Models
by: Gu, Tianle, et al.
Published: (2024)

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

Auto-Tuning Safety Guardrails for Black-Box Large Language Models
by: Abdulkadir, Perry
Published: (2025)