Imagen de Portada

Safety at One Shot: Patching Fine-Tuned LLMs with A Single Instance

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Zhang, Jiawen, He, Lipeng, Chen, Kejia, Lou, Jian, Liu, Jian, Yang, Xiaohu, Jia, Ruoxi
Formato:	Preprint
Publicado:	2026
Materias:	Machine Learning Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Understanding and Preserving Safety in Fine-Tuned LLMs
por: Zhang, Jiawen, et al.
Publicado: (2026)

Q-resafe: Assessing Safety Risks and Quantization-aware Safety Patching for Quantized Large Language Models
por: Chen, Kejia, et al.
Publicado: (2025)

Activation Approximations Can Incur Safety Vulnerabilities Even in Aligned LLMs: Comprehensive Analysis and Defense
por: Zhang, Jiawen, et al.
Publicado: (2025)

Mitigating Many-shot Jailbreak Attacks with One Single Demonstration
por: Chen, Kejia, et al.
Publicado: (2026)

Confidence-Aware Alignment Makes Reasoning LLMs More Reliable
por: Chen, Kejia, et al.
Publicado: (2026)

SecPE: Secure Prompt Ensembling for Private and Robust Large Language Models
por: Zhang, Jiawen, et al.
Publicado: (2025)

Just Enough Shifts: Mitigating Over-Refusal in Aligned Language Models with Targeted Representation Fine-Tuning
por: Dabas, Mahavir, et al.
Publicado: (2025)

Get more for less: Principled Data Selection for Warming Up Fine-Tuning in LLMs
por: Kang, Feiyang, et al.
Publicado: (2024)

Safe Delta: Consistently Preserving Safety when Fine-Tuning LLMs on Diverse Datasets
por: Lu, Ning, et al.
Publicado: (2025)

Active Few-Shot Fine-Tuning
por: Hübotter, Jonas, et al.
Publicado: (2024)

One-Shot Price Forecasting with Covariate-Guided Experts under Privacy Constraints
por: He, Ren, et al.
Publicado: (2026)

Safety Mirage: How Spurious Correlations Undermine VLM Safety Fine-Tuning and Can Be Mitigated by Machine Unlearning
por: Chen, Yiwei, et al.
Publicado: (2025)

Aligning LLMs with Biomedical Knowledge using Balanced Fine-Tuning
por: Tang, Zhenchao, et al.
Publicado: (2025)

Zeroth-Order Fine-Tuning of LLMs in Random Subspaces
por: Yu, Ziming, et al.
Publicado: (2024)

LoRA-One: One-Step Full Gradient Could Suffice for Fine-Tuning Large Language Models, Provably and Efficiently
por: Zhang, Yuanhe, et al.
Publicado: (2025)

Zeroth-Order Fine-Tuning of LLMs with Extreme Sparsity
por: Guo, Wentao, et al.
Publicado: (2024)

Robust and Efficient Zeroth-Order LLM Fine-Tuning via Adaptive Bayesian Subspace Optimizer
por: Feng, Jian, et al.
Publicado: (2026)

NeuronTune: Fine-Grained Neuron Modulation for Balanced Safety-Utility Alignment in LLMs
por: Pan, Birong, et al.
Publicado: (2025)

Efficiency vs. Alignment: Investigating Safety and Fairness Risks in Parameter-Efficient Fine-Tuning of LLMs
por: Taraghi, Mina, et al.
Publicado: (2025)

CTIGuardian: A Few-Shot Framework for Mitigating Privacy Leakage in Fine-Tuned LLMs
por: Arachchige, Shashie Dilhara Batan, et al.
Publicado: (2025)

Self-Mined Hardness for Safety Fine-Tuning
por: Gupta, Prakhar, et al.
Publicado: (2026)

Federated Fine-Tuning of LLMs: Framework Comparison and Research Directions
por: Yan, Na, et al.
Publicado: (2025)

SHAPE : Self-Improved Visual Preference Alignment by Iteratively Generating Holistic Winner
por: Chen, Kejia, et al.
Publicado: (2025)

Position-Aware Parameter Efficient Fine-Tuning Approach for Reducing Positional Bias in LLMs
por: Zhang, Zheng, et al.
Publicado: (2024)

Quantum-Inspired Fine-Tuning for Few-Shot AIGC Detection via Phase-Structured Reparameterization
por: Xing, Kaiyang, et al.
Publicado: (2026)

Thompson Sampling via Fine-Tuning of LLMs
por: Menet, Nicolas, et al.
Publicado: (2025)

Re-Emergent Misalignment: How Narrow Fine-Tuning Erodes Safety Alignment in LLMs
por: Giordani, Jeremiah
Publicado: (2025)

vTune: Verifiable Fine-Tuning for LLMs Through Backdooring
por: Zhang, Eva, et al.
Publicado: (2024)

Silent Sabotage During Fine-Tuning: Few-Shot Rationale Poisoning of Compact Medical LLMs
por: Xie, Jingyuan, et al.
Publicado: (2026)

SafeTuneBed: A Toolkit for Benchmarking LLM Safety Alignment in Fine-Tuning
por: Hossain, Saad, et al.
Publicado: (2025)

The Geometry of Alignment Collapse: When Fine-Tuning Breaks Safety
por: Springer, Max, et al.
Publicado: (2026)

RevFFN: Memory-Efficient Full-Parameter Fine-Tuning of Mixture-of-Experts LLMs with Reversible Blocks
por: Liu, Ningyuan, et al.
Publicado: (2025)

Probing Knowledge Holes in Unlearned LLMs
por: Ko, Myeongseob, et al.
Publicado: (2025)

FedProxy: Federated Fine-Tuning of LLMs via Proxy SLMs and Heterogeneity-Aware Fusion
por: Fan, Tao, et al.
Publicado: (2026)

Token-Level Inference-Time Alignment for Vision-Language Models
por: Chen, Kejia, et al.
Publicado: (2025)

Parameter-Efficient Fine-Tuning of LLMs with Mixture of Space Experts
por: Zhang, Buze, et al.
Publicado: (2026)

VAR-MATH: Probing True Mathematical Reasoning in LLMS via Symbolic Multi-Instance Benchmarks
por: Yao, Jian, et al.
Publicado: (2025)

CLoQ: Enhancing Fine-Tuning of Quantized LLMs via Calibrated LoRA Initialization
por: Deng, Yanxia, et al.
Publicado: (2025)

Efficiently Learning at Test-Time: Active Fine-Tuning of LLMs
por: Hübotter, Jonas, et al.
Publicado: (2024)

Explaining Fine Tuned LLMs via Counterfactuals A Knowledge Graph Driven Framework
por: Wang, Yucheng, et al.
Publicado: (2025)