Copertina

Safety Alignment via Constrained Knowledge Unlearning

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Shi, Zesheng, Zhou, Yucheng, Li, Jing
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Computation and Language Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

RAGA: Reading-And-Graph-building-Agent for Autonomous Knowledge Graph Construction and Retrieval-Augmented Generation
di: Han, Chengrui, et al.
Pubblicazione: (2026)

Team-Based Self-Play With Dual Adaptive Weighting for Fine-Tuning LLMs
di: Li, Wu, et al.
Pubblicazione: (2026)

SHA256 at SemEval-2025 Task 4: Selective Amnesia -- Constrained Unlearning for Large Language Models via Knowledge Isolation
di: Agrawal, Saransh, et al.
Pubblicazione: (2025)

R1-ACT: Efficient Reasoning Model Safety Alignment by Activating Safety Knowledge
di: In, Yeonjun, et al.
Pubblicazione: (2025)

Knowledge-Level Consistency Reinforcement Learning: Dual-Fact Alignment for Long-Form Factuality
di: Li, Junliang, et al.
Pubblicazione: (2025)

Constrain Alignment with Sparse Autoencoders
di: Yin, Qingyu, et al.
Pubblicazione: (2024)

Learning and Unlearning of Fabricated Knowledge in Language Models
di: Sun, Chen, et al.
Pubblicazione: (2024)

Knowledge Fusion of Large Language Models Via Modular SkillPacks
di: Du, Guodong, et al.
Pubblicazione: (2025)

Bridging the Gap Between Preference Alignment and Machine Unlearning
di: Feng, Xiaohua, et al.
Pubblicazione: (2025)

Safety Compliance: Rethinking LLM Safety Reasoning through the Lens of Compliance
di: Hu, Wenbin, et al.
Pubblicazione: (2025)

Intrinsic Test of Unlearning Using Parametric Knowledge Traces
di: Hong, Yihuai, et al.
Pubblicazione: (2024)

Multilingual Safety Alignment via Self-Distillation
di: Qin, Ruiyang, et al.
Pubblicazione: (2026)

Circumventing Safety Alignment in Large Language Models Through Embedding Space Toxicity Attenuation
di: Zhang, Zhibo, et al.
Pubblicazione: (2025)

Enhancing Large Language Model for Knowledge Graph Completion via Structure-Aware Alignment-Tuning
di: Liu, Yu, et al.
Pubblicazione: (2025)

Safety Is Not Universal: The Selective Safety Trap in LLM Alignment
di: Brito, Iago Alves, et al.
Pubblicazione: (2026)

Efficient Knowledge Infusion via KG-LLM Alignment
di: Jiang, Zhouyu, et al.
Pubblicazione: (2024)

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

Cat-DPO: Category-Adaptive Safety Alignment
di: Yang, Tiankai, et al.
Pubblicazione: (2026)

ZeroUnlearn: Few-Shot Knowledge Unlearning in Large Language Models
di: Lin, Yujie, et al.
Pubblicazione: (2026)

Catastrophic Failure of LLM Unlearning via Quantization
di: Zhang, Zhiwei, et al.
Pubblicazione: (2024)

MKRAG: Medical Knowledge Retrieval Augmented Generation for Medical Question Answering
di: Shi, Yucheng, et al.
Pubblicazione: (2023)

SafeSteer: Localized On-Policy Distillation for Efficient Safety Alignment
di: Li, Hao, et al.
Pubblicazione: (2026)

Controllable Safety Alignment: Inference-Time Adaptation to Diverse Safety Requirements
di: Zhang, Jingyu, et al.
Pubblicazione: (2024)

LLM Surgery: Efficient Knowledge Unlearning and Editing in Large Language Models
di: Veldanda, Akshaj Kumar, et al.
Pubblicazione: (2024)

Psychometric Alignment: Capturing Human Knowledge Distributions via Language Models
di: He-Yueya, Joy, et al.
Pubblicazione: (2024)

AlphaEdit: Null-Space Constrained Knowledge Editing for Language Models
di: Fang, Junfeng, et al.
Pubblicazione: (2024)

Self-Guided Defense: Adaptive Safety Alignment for Reasoning Models via Synthesized Guidelines
di: Wang, Yuhang, et al.
Pubblicazione: (2025)

Beyond Reactive Safety: Risk-Aware LLM Alignment via Long-Horizon Simulation
di: Sun, Chenkai, et al.
Pubblicazione: (2025)

Adapting LLMs to Time Series Forecasting via Temporal Heterogeneity Modeling and Semantic Alignment
di: Sun, Yanru, et al.
Pubblicazione: (2025)

SafeWorld: Geo-Diverse Safety Alignment
di: Yin, Da, et al.
Pubblicazione: (2024)

Retrieval-enhanced Knowledge Editing in Language Models for Multi-Hop Question Answering
di: Shi, Yucheng, et al.
Pubblicazione: (2024)

Unforgotten Safety: Preserving Safety Alignment of Large Language Models with Continual Learning
di: Alssum, Lama, et al.
Pubblicazione: (2025)

Two Heads Are Better Than One: Integrating Knowledge from Knowledge Graphs and Large Language Models for Entity Alignment
di: Yang, Linyao, et al.
Pubblicazione: (2024)

HOMURA: Taming the Sand-Glass for Time-Constrained LLM Translation via Reinforcement Learning
di: Cui, Ziang, et al.
Pubblicazione: (2026)

What Matters For Safety Alignment?
di: Li, Xing, et al.
Pubblicazione: (2026)

Does Machine Unlearning Truly Remove Knowledge?
di: Chen, Haokun, et al.
Pubblicazione: (2025)

The Hidden Dimensions of LLM Alignment: A Multi-Dimensional Analysis of Orthogonal Safety Directions
di: Pan, Wenbo, et al.
Pubblicazione: (2025)

Precision Knowledge Editing: Enhancing Safety in Large Language Models
di: Li, Xuying, et al.
Pubblicazione: (2024)

PKU-SafeRLHF: Towards Multi-Level Safety Alignment for LLMs with Human Preference
di: Ji, Jiaming, et al.
Pubblicazione: (2024)

MESA: Improving MoE Safety Alignment via Decentralized Expertise
di: Sun, Yitong, et al.
Pubblicazione: (2026)