Copertina

Separate the Wheat from the Chaff: A Post-Hoc Approach to Safety Re-Alignment for Fine-Tuned Language Models

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Wu, Di, Lu, Xin, Zhao, Yanyan, Qin, Bing
Natura:	Preprint
Pubblicazione:	2024
Soggetti:	Computation and Language
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

STAR-S: Improving Safety Alignment through Self-Taught Reasoning on Safety Rules
di: Wu, Di, et al.
Pubblicazione: (2026)

Separate the Wheat from the Chaff: Model Deficiency Unlearning via Parameter-Efficient Module Operation
di: Hu, Xinshuo, et al.
Pubblicazione: (2023)

Towards Comprehensive Post Safety Alignment of Large Language Models via Safety Patching
di: Zhao, Weixiang, et al.
Pubblicazione: (2024)

Separating the Wheat from the Chaff: Understanding (In-)Completeness of Proof Mechanisms for Separation Logic with Inductive Definitions
di: Elad, Neta, et al.
Pubblicazione: (2025)

Separate the Wheat from the Chaff: Winnowing Down Divergent Views in Retrieval Augmented Generation
di: Wang, Song, et al.
Pubblicazione: (2025)

Separating the Wheat from the Chaff
di: Hörner, Johannes, et al.
Pubblicazione: (2026)

Beware of Your Po! Measuring and Mitigating AI Safety Risks in Role-Play Fine-Tuning of LLMs
di: Zhao, Weixiang, et al.
Pubblicazione: (2025)

Rethinking Bottlenecks in Safety Fine-Tuning of Vision Language Models
di: Ding, Yi, et al.
Pubblicazione: (2025)

Improving the Downstream Performance of Mixture-of-Experts Transformers via Weak Vanilla Transformers
di: Lu, Xin, et al.
Pubblicazione: (2024)

How does Architecture Influence the Base Capabilities of Pre-trained Language Models? A Case Study Based on FFN-Wider and MoE Transformers
di: Lu, Xin, et al.
Pubblicazione: (2024)

How Does Sequence Modeling Architecture Influence Base Capabilities of Pre-trained Language Models? Exploring Key Architecture Design Principles to Avoid Base Capabilities Degradation
di: Lu, Xin, et al.
Pubblicazione: (2025)

MPO: Multilingual Safety Alignment via Reward Gap Optimization
di: Zhao, Weixiang, et al.
Pubblicazione: (2025)

Teaching Language Models to Evolve with Users: Dynamic Profile Modeling for Personalized Alignment
di: Zhao, Weixiang, et al.
Pubblicazione: (2025)

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

Language Models are Homer Simpson! Safety Re-Alignment of Fine-tuned Language Models through Task Arithmetic
di: Bhardwaj, Rishabh, et al.
Pubblicazione: (2024)

Separating the Wheat from the Chaff: Internet Quality.
di: Skov, Annette
Pubblicazione: (1998)

Fine-Tuning Language Models for Ethical Ambiguity: A Comparative Study of Alignment with Human Responses
di: Senthilkumar, Pranav, et al.
Pubblicazione: (2024)

DeepSight: Bridging Depth Maps and Language with a Depth-Driven Multimodal Model
di: Yang, Hao, et al.
Pubblicazione: (2026)

Decomposition-Enhanced Training for Post-Hoc Attributions In Language Models
di: Balasubramanian, Sriram, et al.
Pubblicazione: (2025)

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

Toward Secure Tuning: Mitigating Security Risks from Instruction Fine-Tuning
di: Du, Yanrui, et al.
Pubblicazione: (2024)

NLSR: Neuron-Level Safety Realignment of Large Language Models Against Harmful Fine-Tuning
di: Yi, Xin, et al.
Pubblicazione: (2024)

RKLD: Reverse KL-Divergence-based Knowledge Distillation for Unlearning Personal Information in Large Language Models
di: Wang, Bichen, et al.
Pubblicazione: (2024)

GR-SAP: Generative Replay for Safety Alignment Preservation during Fine-Tuning
di: Fang, Zhouxiang, et al.
Pubblicazione: (2026)

How Good is Post-Hoc Watermarking With Language Model Rephrasing?
di: Fernandez, Pierre, et al.
Pubblicazione: (2025)

LangGPS: Language Separability Guided Data Pre-Selection for Joint Multilingual Instruction Tuning
di: Ye, Yangfan, et al.
Pubblicazione: (2025)

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

Safety Alignment of Large Language Models via Contrasting Safe and Harmful Distributions
di: Zhang, Xiaoyun, et al.
Pubblicazione: (2024)

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

Scaling Data Diversity for Fine-Tuning Language Models in Human Alignment
di: Song, Feifan, et al.
Pubblicazione: (2024)

Lifelong Safety Alignment for Language Models
di: Wang, Haoyu, et al.
Pubblicazione: (2025)

Safeguard Fine-Tuned LLMs Through Pre- and Post-Tuning Model Merging
di: Farn, Hua, et al.
Pubblicazione: (2024)

Rethinking Experience Utilization in Self-Evolving Language Model Agents
di: Zhao, Weixiang, et al.
Pubblicazione: (2026)

Enhancing Non-English Capabilities of English-Centric Large Language Models through Deep Supervision Fine-Tuning
di: Huo, Wenshuai, et al.
Pubblicazione: (2025)

LegiLM: A Fine-Tuned Legal Language Model for Data Compliance
di: Zhu, Linkai, et al.
Pubblicazione: (2024)

AlignTune: Modular Toolkit for Post-Training Alignment of Large Language Models
di: Lyngkhoi, R E Zera Marveen, et al.
Pubblicazione: (2026)

EdgeFlowerTune: Evaluating Federated LLM Fine-Tuning Under Realistic Edge System Constraints
di: Geng, Jiaxiang, et al.
Pubblicazione: (2026)

ReFT: Reasoning with Reinforced Fine-Tuning
di: Luong, Trung Quoc, et al.
Pubblicazione: (2024)

Large Language Model Agents Are Not Always Faithful Self-Evolvers
di: Zhao, Weixiang, et al.
Pubblicazione: (2026)

Self-AMPLIFY: Improving Small Language Models with Self Post Hoc Explanations
di: Bhan, Milan, et al.
Pubblicazione: (2024)