Buchumschlag

Language Models are Homer Simpson! Safety Re-Alignment of Fine-tuned Language Models through Task Arithmetic

Fuente: arXiv

Gespeichert in:

Bibliographische Detailangaben
Hauptverfasser:	Bhardwaj, Rishabh, Anh, Do Duc, Poria, Soujanya
Format:	Preprint
Veröffentlicht:	2024
Schlagworte:	Computation and Language Artificial Intelligence
Online-Zugang:	Acceder al recurso
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Ähnliche Einträge

Towards Robust Instruction Tuning on Multimodal Large Language Models
von: Han, Wei, et al.
Veröffentlicht: (2024)

WalledEval: A Comprehensive Safety Evaluation Toolkit for Large Language Models
von: Gupta, Prannaya, et al.
Veröffentlicht: (2024)

Safety Arithmetic: A Framework for Test-time Safety Alignment of Language Models by Steering Parameters and Activations
von: Hazra, Rima, et al.
Veröffentlicht: (2024)

DELLA-Merging: Reducing Interference in Model Merging through Magnitude-Based Sampling
von: Deep, Pala Tej, et al.
Veröffentlicht: (2024)

Large Language Models for Automated Open-domain Scientific Hypotheses Discovery
von: Yang, Zonglin, et al.
Veröffentlicht: (2023)

Post Reasoning: Improving the Performance of Non-Thinking Models at No Cost
von: Xuan, Richmond Sin Jing, et al.
Veröffentlicht: (2026)

Federated Fine-tuning of Large Language Models under Heterogeneous Tasks and Client Resources
von: Bai, Jiamu, et al.
Veröffentlicht: (2024)

Error Typing for Smarter Rewards: Improving Process Reward Models with Error-Aware Hierarchical Supervision
von: Pala, Tej Deep, et al.
Veröffentlicht: (2025)

Stacked from One: Multi-Scale Self-Injection for Context Window Extension
von: Han, Wei, et al.
Veröffentlicht: (2026)

Fundamental Safety-Capability Trade-offs in Fine-tuning Large Language Models
von: Chen, Pin-Yu, et al.
Veröffentlicht: (2025)

Semi-supervised Fine-tuning for Large Language Models
von: Luo, Junyu, et al.
Veröffentlicht: (2024)

Ruby Teaming: Improving Quality Diversity Search with Memory for Automated Red Teaming
von: Han, Vernon Toh Yan, et al.
Veröffentlicht: (2024)

Bias Vector: Mitigating Biases in Language Models with Task Arithmetic Approach
von: Shirafuji, Daiki, et al.
Veröffentlicht: (2024)

Fine-tuning Transformer-based Encoder for Turkish Language Understanding Tasks
von: Yildirim, Savas
Veröffentlicht: (2024)

Language Models Do Hard Arithmetic Tasks Easily and Hardly Do Easy Arithmetic Tasks
von: Gambardella, Andrew, et al.
Veröffentlicht: (2024)

Plug-in and Fine-tuning: Bridging the Gap between Small Language Models and Large Language Models
von: Kim, Kyeonghyun, et al.
Veröffentlicht: (2025)

Small Language Models Fine-tuned to Coordinate Larger Language Models improve Complex Reasoning
von: Juneja, Gurusha, et al.
Veröffentlicht: (2023)

Advancing Single and Multi-task Text Classification through Large Language Model Fine-tuning
von: Zhao, Hang, et al.
Veröffentlicht: (2024)

Sensitivity of Small Language Models to Fine-tuning Data Contamination
von: Scaria, Nicy, et al.
Veröffentlicht: (2025)

Toward Robust Multimodal Learning using Multimodal Foundational Models
von: Zhao, Xianbing, et al.
Veröffentlicht: (2024)

Exploring Memorization in Fine-tuned Language Models
von: Zeng, Shenglai, et al.
Veröffentlicht: (2023)

SC-Phi2: A Fine-tuned Small Language Model for StarCraft II Macromanagement Tasks
von: Khan, Muhammad Junaid, et al.
Veröffentlicht: (2024)

Self-Adaptive Sampling for Efficient Video Question-Answering on Image--Text Models
von: Han, Wei, et al.
Veröffentlicht: (2023)

MOOSE-Chem: Large Language Models for Rediscovering Unseen Chemistry Scientific Hypotheses
von: Yang, Zonglin, et al.
Veröffentlicht: (2024)

Can-Do! A Dataset and Neuro-Symbolic Grounded Framework for Embodied Planning with Large Multimodal Models
von: Chia, Yew Ken, et al.
Veröffentlicht: (2024)

KnowTuning: Knowledge-aware Fine-tuning for Large Language Models
von: Lyu, Yougang, et al.
Veröffentlicht: (2024)

Progtuning: Progressive Fine-tuning Framework for Transformer-based Language Models
von: Ji, Xiaoshuang, et al.
Veröffentlicht: (2025)

JudgeLM: Fine-tuned Large Language Models are Scalable Judges
von: Zhu, Lianghui, et al.
Veröffentlicht: (2023)

Dhati+: Fine-tuned Large Language Models for Arabic Subjectivity Evaluation
von: Bellaouar, Slimane, et al.
Veröffentlicht: (2025)

Compositional Subspace Representation Fine-tuning for Adaptive Large Language Models
von: Zhou, Andy
Veröffentlicht: (2025)

OffTopicEval: When Large Language Models Enter the Wrong Chat, Almost Always!
von: Lei, Jingdi, et al.
Veröffentlicht: (2025)

Task Arithmetic for Language Expansion in Speech Translation
von: Cheng, Yao-Fei, et al.
Veröffentlicht: (2024)

Fine-tuning Language Models with Generative Adversarial Reward Modelling
von: Yu, Zhang Ze, et al.
Veröffentlicht: (2023)

Safety-Aware Fine-Tuning of Large Language Models
von: Choi, Hyeong Kyu, et al.
Veröffentlicht: (2024)

Using Large Language Models for education managements in Vietnamese with low resources
von: Minh, Duc Do, et al.
Veröffentlicht: (2025)

Probing for Arithmetic Errors in Language Models
von: Sun, Yucheng, et al.
Veröffentlicht: (2025)

Two are better than one: Context window extension with multi-grained self-injection
von: Han, Wei, et al.
Veröffentlicht: (2024)

Panacea: Mitigating Harmful Fine-tuning for Large Language Models via Post-fine-tuning Perturbation
von: Wang, Yibo, et al.
Veröffentlicht: (2025)

Information Guided Regularization for Fine-tuning Language Models
von: Sharma, Mandar, et al.
Veröffentlicht: (2024)

SafeMERGE: Preserving Safety Alignment in Fine-Tuned Large Language Models via Selective Layer-Wise Model Merging
von: Djuhera, Aladin, et al.
Veröffentlicht: (2025)