Imagen de Portada

Self-Guided Defense: Adaptive Safety Alignment for Reasoning Models via Synthesized Guidelines

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Wang, Yuhang, Zhu, Yanxu, Lu, Dongyuan, Sang, Jitao
Formato:	Preprint
Publicado:	2025
Materias:	Computation and Language Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Reasoning Shapes Alignment: Investigating Cultural Alignment in Large Reasoning Models with Cultural Norms
por: Wang, Yuhang, et al.
Publicado: (2025)

KG-FPQ: Evaluating Factuality Hallucination in LLMs with Knowledge Graph-based False Premise Questions
por: Zhu, Yanxu, et al.
Publicado: (2024)

Don't Command, Cultivate: An Exploratory Study of System-2 Alignment
por: Wang, Yuhang, et al.
Publicado: (2024)

Inference-Time Rule Eraser: Fair Recognition via Distilling and Removing Biased Rules
por: Zhang, Yi, et al.
Publicado: (2024)

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

Safety Reasoning with Guidelines
por: Wang, Haoyu, et al.
Publicado: (2025)

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

Prescribing the Right Remedy: Mitigating Hallucinations in Large Vision-Language Models via Targeted Instruction Tuning
por: Hu, Rui, et al.
Publicado: (2024)

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

When Models Outthink Their Safety: Unveiling and Mitigating Self-Jailbreak in Large Reasoning Models
por: Mao, Yingzhi, et al.
Publicado: (2025)

Mitigating the Safety-utility Trade-off in LLM Alignment via Adaptive Safe Context Learning
por: Wang, Yanbo, et al.
Publicado: (2026)

Reasoning Pattern Alignment Merging for Adaptive Reasoning
por: Zhong, Zhaofeng, et al.
Publicado: (2026)

AdvChain: Adversarial Chain-of-Thought Tuning for Robust Safety Alignment of Large Reasoning Models
por: Zhu, Zihao, et al.
Publicado: (2025)

CliCARE: Grounding Large Language Models in Clinical Guidelines for Decision Support over Longitudinal Cancer Electronic Health Records
por: Li, Dongchen, et al.
Publicado: (2025)

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

Mobile-Agent-V: A Video-Guided Approach for Effortless and Efficient Operational Knowledge Injection in Mobile Automation
por: Wang, Junyang, et al.
Publicado: (2025)

On-the-fly Preference Alignment via Principle-Guided Decoding
por: Zhu, Mingye, et al.
Publicado: (2025)

Provable Defense Framework for LLM Jailbreaks via Noise-Augumented Alignment
por: Cheng, Zehua, et al.
Publicado: (2026)

Diverse Human Value Alignment for Large Language Models via Ethical Reasoning
por: Wang, Jiahao, et al.
Publicado: (2025)

Safety Alignment via Constrained Knowledge Unlearning
por: Shi, Zesheng, et al.
Publicado: (2025)

Towards Context-Invariant Safety Alignment for Large Language Models
por: Wang, Yixu, et al.
Publicado: (2026)

Direct Alignment of Language Models via Quality-Aware Self-Refinement
por: Yu, Runsheng, et al.
Publicado: (2024)

Positional Failures in Long-Context LLMs: A Blind Spot in Reasoning Benchmarks
por: Zhang, Chuyifei, et al.
Publicado: (2026)

SLAM: Towards Efficient Multilingual Reasoning via Selective Language Alignment
por: Fan, Yuchun, et al.
Publicado: (2025)

ReasoningShield: Safety Detection over Reasoning Traces of Large Reasoning Models
por: Li, Changyi, et al.
Publicado: (2025)

CDEval: A Benchmark for Measuring the Cultural Dimensions of Large Language Models
por: Wang, Yuhang, et al.
Publicado: (2023)

SelfAug: Mitigating Catastrophic Forgetting in Retrieval-Augmented Generation via Distribution Self-Alignment
por: Huang, Yuqing, et al.
Publicado: (2025)

Mitigating Catastrophic Forgetting in Large Language Models with Self-Synthesized Rehearsal
por: Huang, Jianheng, et al.
Publicado: (2024)

Recon: Reconstruction-Guided Reasoning Synthesis for User Modeling
por: Zhu, Alan, et al.
Publicado: (2026)

ARise: Towards Knowledge-Augmented Reasoning via Risk-Adaptive Search
por: Zhang, Yize, et al.
Publicado: (2025)

GEGA: Graph Convolutional Networks and Evidence Retrieval Guided Attention for Enhanced Document-level Relation Extraction
por: Mao, Yanxu, et al.
Publicado: (2024)

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

Refining Positive and Toxic Samples for Dual Safety Self-Alignment of LLMs with Minimal Human Interventions
por: Xu, Jingxin, et al.
Publicado: (2025)

SelfPrompt: Autonomously Evaluating LLM Robustness via Domain-Constrained Knowledge Guidelines and Refined Adversarial Prompts
por: Pei, Aihua, et al.
Publicado: (2024)

Towards Concise and Adaptive Thinking in Large Reasoning Models: A Survey
por: Zhu, Jason, et al.
Publicado: (2025)

ReasoningGuard: Safeguarding Large Reasoning Models with Inference-time Safety Aha Moments
por: Wang, Yuquan, et al.
Publicado: (2025)

SynthesizeMe! Inducing Persona-Guided Prompts for Personalized Reward Models in LLMs
por: Ryan, Michael J, et al.
Publicado: (2025)

Unifying Ontology Construction and Semantic Alignment for Deterministic Enterprise Reasoning at Scale
por: Zhu, Hongyin
Publicado: (2026)

GRACE: Discriminator-Guided Chain-of-Thought Reasoning
por: Khalifa, Muhammad, et al.
Publicado: (2023)

Efficient Reasoning for Large Reasoning Language Models via Certainty-Guided Reflection Suppression
por: Huang, Jiameng, et al.
Publicado: (2025)