Cover Image

Self and Cross-Model Distillation for LLMs: Effective Methods for Refusal Pattern Alignment

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Li, Jie, Liu, Yi, Liu, Chongyang, Ren, Xiaoning, Shi, Ling, Sun, Weisong, Xue, Yinxing
Format:	Preprint
Published:	2024
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

A Cross-Language Investigation into Jailbreak Attacks in Large Language Models
by: Li, Jie, et al.
Published: (2024)

Do Reasoning LLMs Refuse What They Infer in Long Contexts?
by: Fu, Yu, et al.
Published: (2026)

Beyond Surface Alignment: Rebuilding LLMs Safety Mechanism via Probabilistically Ablating Refusal Direction
by: Xie, Yuanbo, et al.
Published: (2025)

The Art of (Mis)alignment: How Fine-Tuning Methods Effectively Misalign and Realign LLMs in Post-Training
by: Zhang, Rui, et al.
Published: (2026)

From Threat to Tool: Leveraging Refusal-Aware Injection Attacks for Safety Alignment
by: Chae, Kyubyung, et al.
Published: (2025)

Evolve the Method, Not the Prompts: Evolutionary Synthesis of Jailbreak Attacks on LLMs
by: Chen, Yunhao, et al.
Published: (2025)

Logit-Gap Steering: A Forward-Pass Diagnostic for Alignment Robustness
by: Li, Tung-Ling, et al.
Published: (2025)

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

Safety is Not Only About Refusal: Reasoning-Enhanced Fine-tuning for Interpretable LLM Safety
by: Zhang, Yuyou, et al.
Published: (2025)

LLMs Can Unlearn Refusal with Only 1,000 Benign Samples
by: Guo, Yangyang, et al.
Published: (2026)

Effective and Efficient Jailbreaks of Black-Box LLMs with Cross-Behavior Attacks
by: Gohil, Vasudev
Published: (2025)

Beyond Text: Unveiling Privacy Vulnerabilities in Multi-modal Retrieval-Augmented Generation
by: Zhang, Jiankun, et al.
Published: (2025)

Efficient and Stealthy Jailbreak Attacks via Adversarial Prompt Distillation from LLMs to SLMs
by: Li, Xiang, et al.
Published: (2025)

Image-Based Geolocation Using Large Vision-Language Models
by: Liu, Yi, et al.
Published: (2024)

A Content-Based Framework for Cybersecurity Refusal Decisions in Large Language Models
by: Linder, Noa, et al.
Published: (2026)

HackWorld: Evaluating Computer-Use Agents on Exploiting Web Application Vulnerabilities
by: Ren, Xiaoxue, et al.
Published: (2025)

Self-Jailbreaking: Language Models Can Reason Themselves Out of Safety Alignment After Benign Reasoning Training
by: Yong, Zheng-Xin, et al.
Published: (2025)

One Model Transfer to All: On Robust Jailbreak Prompts Generation against LLMs
by: Li, Linbao, et al.
Published: (2025)

Beyond Pattern Matching: Seven Cross-Domain Techniques for Prompt Injection Detection
by: Munirathinam, Thamilvendhan
Published: (2026)

Cross-Task Defense: Instruction-Tuning LLMs for Content Safety
by: Fu, Yu, et al.
Published: (2024)

Dynamic Adversarial Fine-Tuning Reorganizes Refusal Geometry
by: Lan, Wenhao, et al.
Published: (2026)

Efficient Detection of Toxic Prompts in Large Language Models
by: Liu, Yi, et al.
Published: (2024)

Mitigating Jailbreaks with Intent-Aware LLMs
by: Yeo, Wei Jie, et al.
Published: (2025)

Omni-Safety under Cross-Modality Conflict: Vulnerabilities, Dynamics Mechanisms and Efficient Alignment
by: Wang, Kun, et al.
Published: (2026)

Tracing the Dynamics of Refusal: Exploiting Latent Refusal Trajectories for Robust Jailbreak Detection
by: Hu, Xulin, et al.
Published: (2026)

A Simple and Efficient Jailbreak Method Exploiting LLMs' Helpfulness
by: Luo, Xuan, et al.
Published: (2025)

Gradient Cuff: Detecting Jailbreak Attacks on Large Language Models by Exploring Refusal Loss Landscapes
by: Hu, Xiaomeng, et al.
Published: (2024)

Continuous Embedding Attacks via Clipped Inputs in Jailbreaking Large Language Models
by: Xu, Zihao, et al.
Published: (2024)

TuBA: Cross-Lingual Transferability of Backdoor Attacks in LLMs with Instruction Tuning
by: He, Xuanli, et al.
Published: (2024)

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

FFT: Towards Harmlessness Evaluation and Analysis for LLMs with Factuality, Fairness, Toxicity
by: Cui, Shiyao, et al.
Published: (2023)

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

Dataset Protection via Watermarked Canaries in Retrieval-Augmented LLMs
by: Liu, Yepeng, et al.
Published: (2025)

Unlearning Backdoor Attacks for LLMs with Weak-to-Strong Knowledge Distillation
by: Zhao, Shuai, et al.
Published: (2024)

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

Semantic-Preserving Adversarial Attacks on LLMs: An Adaptive Greedy Binary Search Approach
by: Zhang, Chong, et al.
Published: (2025)

Demystifying Invariant Effectiveness for Securing Smart Contracts
by: Chen, Zhiyang, et al.
Published: (2024)

"Yes, My LoRD." Guiding Language Model Extraction with Locality Reinforced Distillation
by: Liang, Zi, et al.
Published: (2024)

Enhancing Prompt Injection Attacks to LLMs via Poisoning Alignment
by: Shao, Zedian, et al.
Published: (2024)

Jailbreaking Commercial Black-Box LLMs with Explicitly Harmful Prompts
by: Zhang, Chiyu, et al.
Published: (2025)