Cover Image

Learning to Stay Safe: Adaptive Regularization Against Safety Degradation during Fine-Tuning

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Goel, Jyotin, Maji, Souvik, Mazumder, Pratik
Format:	Preprint
Published:	2026
Subjects:	Computation and Language Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

SafeCOMM: A Study on Safety Degradation in Fine-Tuned Telecom Large Language Models
by: Djuhera, Aladin, et al.
Published: (2025)

Learning While Staying Curious: Entropy-Preserving Supervised Fine-Tuning via Adaptive Self-Distillation for Large Reasoning Models
by: Wang, Hao, et al.
Published: (2026)

AFLoRA: Adaptive Freezing of Low Rank Adaptation in Parameter Efficient Fine-Tuning of Large Models
by: Liu, Zeyu, et al.
Published: (2024)

LaMDA: Large Model Fine-Tuning via Spectrally Decomposed Low-Dimensional Adaptation
by: Azizi, Seyedarmin, et al.
Published: (2024)

Understanding the Performance and Estimating the Cost of LLM Fine-Tuning
by: Xia, Yuchen, et al.
Published: (2024)

Objective Matters: Fine-Tuning Objectives Shape Safety, Robustness, and Persona Drift
by: Vennemeyer, Daniel, et al.
Published: (2026)

Semantic-Anchored, Class Variance-Optimized Clustering for Robust Semi-Supervised Few-Shot Learning
by: Maji, Souvik, et al.
Published: (2025)

Direct Alignment of Draft Model for Speculative Decoding with Chat-Fine-Tuned LLMs
by: Goel, Raghavv, et al.
Published: (2024)

Stay Tuned: An Empirical Study of the Impact of Hyperparameters on LLM Tuning in Real-World Applications
by: Halfon, Alon, et al.
Published: (2024)

In-Context Learning and Fine-Tuning GPT for Argument Mining
by: Cabessa, Jérémie, et al.
Published: (2024)

Domain-Adaptive Small Language Models for Structured Tax Code Prediction
by: Nath, Souvik, et al.
Published: (2025)

Safety Subspaces are Not Linearly Distinct: A Fine-Tuning Case Study
by: Ponkshe, Kaustubh, et al.
Published: (2025)

Anchored Supervised Fine-Tuning
by: Zhu, He, et al.
Published: (2025)

LoX: Low-Rank Extrapolation Robustifies LLM Safety Against Fine-tuning
by: Perin, Gabriel J., et al.
Published: (2025)

Advancing LLM Safe Alignment with Safety Representation Ranking
by: Du, Tianqi, et al.
Published: (2025)

Prior-Informed Zeroth-Order Optimization with Adaptive Direction Alignment for Memory-Efficient LLM Fine-Tuning
by: Jin, Feihu, et al.
Published: (2026)

Few Tokens, Big Leverage: Preserving Safety Alignment by Constraining Safety Tokens during Fine-tuning
by: Wang, Guoli, et al.
Published: (2026)

MSSR: Memory-Aware Adaptive Replay for Continual LLM Fine-Tuning
by: Lu, Yiyang, et al.
Published: (2026)

Entropy-Adaptive Fine-Tuning: Resolving Confident Conflicts to Mitigate Forgetting
by: Diao, Muxi, et al.
Published: (2026)

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

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

Prompt Tuning for Natural Language to SQL with Embedding Fine-Tuning and RAG
by: Jang, Jisoo, et al.
Published: (2025)

Token Buncher: Shielding LLMs from Harmful Reinforcement Learning Fine-Tuning
by: Feng, Weitao, et al.
Published: (2025)

Deeper Insights Without Updates: The Power of In-Context Learning Over Fine-Tuning
by: Yin, Qingyu, et al.
Published: (2024)

Supervised Fine-Tuning as Inverse Reinforcement Learning
by: Sun, Hao
Published: (2024)

Regularization Through Reasoning: Systematic Improvements in Language Model Classification via Explanation-Enhanced Fine-Tuning
by: Shah, Vivswan, et al.
Published: (2025)

Fine Tuning Methods for Low-resource Languages
by: Bakkenes, Tim, et al.
Published: (2025)

QEFT: Quantization for Efficient Fine-Tuning of LLMs
by: Lee, Changhun, et al.
Published: (2024)

Energy and Carbon Considerations of Fine-Tuning BERT
by: Wang, Xiaorong, et al.
Published: (2023)

UFT: Unifying Supervised and Reinforcement Fine-Tuning
by: Liu, Mingyang, et al.
Published: (2025)

Pre-training LLM without Learning Rate Decay Enhances Supervised Fine-Tuning
by: Yano, Kazuki, et al.
Published: (2026)

Deep Learning for Medical Text Processing: BERT Model Fine-Tuning and Comparative Study
by: Hu, Jiacheng, et al.
Published: (2024)

ScoNe: Benchmarking Negation Reasoning in Language Models With Fine-Tuning and In-Context Learning
by: She, Jingyuan Selena, et al.
Published: (2023)

Fine-Tuning Language Models with Reward Learning on Policy
by: Lang, Hao, et al.
Published: (2024)

Teaching LLMs How to Learn with Contextual Fine-Tuning
by: Choi, Younwoo, et al.
Published: (2025)

Lifelong and Continual Learning Dialogue Systems
by: Mazumder, Sahisnu, et al.
Published: (2022)

LIFT: Last-Mile Fine-Tuning for Table Explicitation
by: Khaitan, Divij, et al.
Published: (2026)

Causal Fine-Tuning under Latent Confounded Shift
by: Yu, Jialin, et al.
Published: (2024)

Zhyper: Factorized Hypernetworks for Conditioned LLM Fine-Tuning
by: Abdalla, M. H. I., et al.
Published: (2025)

Parameter-Efficient Fine-Tuning via Circular Convolution
by: Chen, Aochuan, et al.
Published: (2024)