Imagen de Portada

R1-ACT: Efficient Reasoning Model Safety Alignment by Activating Safety Knowledge

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	In, Yeonjun, Kim, Wonjoong, Park, Sangwu, Park, Chanyoung
Formato:	Preprint
Publicado:	2025
Materias:	Artificial Intelligence Computation and Language
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Reasoning Structure Matters for Safety Alignment of Reasoning Models
por: In, Yeonjun, et al.
Publicado: (2026)

Beyond the Final Answer: Evaluating the Reasoning Trajectories of Tool-Augmented Agents
por: Kim, Wonjoong, et al.
Publicado: (2025)

SIMPLOT: Enhancing Chart Question Answering by Distilling Essentials
por: Kim, Wonjoong, et al.
Publicado: (2024)

PAIR: Prefix-Aware Internal Reward Model for Multi-Turn Agent Optimization
por: Kim, Wonjoong, et al.
Publicado: (2026)

Is Safety Standard Same for Everyone? User-Specific Safety Evaluation of Large Language Models
por: In, Yeonjun, et al.
Publicado: (2025)

Personalize-then-Store: Benchmarking and Learning Personalized Memory for Long-horizon Agents
por: In, Yeonjun, et al.
Publicado: (2026)

Self-EvolveRec: Self-Evolving Recommender Systems with LLM-based Directional Feedback
por: Kim, Sein, et al.
Publicado: (2026)

Test-Time Training for Visual Foresight Vision-Language-Action Models
por: Park, Sangwu, et al.
Publicado: (2026)

Rethinking Failure Attribution in Multi-Agent Systems: A Multi-Perspective Benchmark and Evaluation
por: In, Yeonjun, et al.
Publicado: (2026)

Revisiting Fake News Detection: Towards Temporality-aware Evaluation by Leveraging Engagement Earliness
por: Kim, Junghoon, et al.
Publicado: (2024)

DSLR: Diversity Enhancement and Structure Learning for Rehearsal-based Graph Continual Learning
por: Choi, Seungyoon, et al.
Publicado: (2024)

CONDESION-BENCH: Conditional Decision-Making of Large Language Models in Compositional Action Space
por: Hwang, Yeonjun, et al.
Publicado: (2026)

SelfJudge: Faster Speculative Decoding via Self-Supervised Judge Verification
por: Yoon, Kanghoon, et al.
Publicado: (2025)

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

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

ProgRAG: Hallucination-Resistant Progressive Retrieval and Reasoning over Knowledge Graphs
por: Park, Minbae, et al.
Publicado: (2025)

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

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

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

SLM as Guardian: Pioneering AI Safety with Small Language Models
por: Kwon, Ohjoon, et al.
Publicado: (2024)

SafeSteer: Localized On-Policy Distillation for Efficient Safety Alignment
por: Li, Hao, 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)

Trojan Activation Attack: Red-Teaming Large Language Models using Activation Steering for Safety-Alignment
por: Wang, Haoran, et al.
Publicado: (2023)

Safety Alignment Can Be Not Superficial With Explicit Safety Signals
por: Li, Jianwei, et al.
Publicado: (2025)

XL-SafetyBench: A Country-Grounded Cross-Cultural Benchmark for LLM Safety and Cultural Sensitivity
por: Choi, Dasol, et al.
Publicado: (2026)

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

Expanding Search Space with Diverse Prompting Agents: An Efficient Sampling Approach for LLM Mathematical Reasoning
por: Lee, Gisang, et al.
Publicado: (2024)

InvThink: Premortem Reasoning for Safer Language Models
por: Kim, Yubin, et al.
Publicado: (2025)

RealSafe-R1: Safety-Aligned DeepSeek-R1 without Compromising Reasoning Capability
por: Zhang, Yichi, et al.
Publicado: (2025)

Adaptive Self-training Framework for Fine-grained Scene Graph Generation
por: Kim, Kibum, et al.
Publicado: (2024)

THINKSAFE: Self-Generated Safety Alignment for Reasoning Models
por: Lee, Seanie, et al.
Publicado: (2026)

Safety Through Reasoning: An Empirical Study of Reasoning Guardrail Models
por: Sreedhar, Makesh Narsimhan, et al.
Publicado: (2025)

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

Superficial Safety Alignment Hypothesis
por: Li, Jianwei, et al.
Publicado: (2024)

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

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

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

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

Hierarchical Deconstruction of LLM Reasoning: A Graph-Based Framework for Analyzing Knowledge Utilization
por: Ko, Miyoung, et al.
Publicado: (2024)

Improving Multi-hop Logical Reasoning in Knowledge Graphs with Context-Aware Query Representation Learning
por: Kim, Jeonghoon, et al.
Publicado: (2024)