Buchumschlag

Towards Safer Large Reasoning Models by Promoting Safety Decision-Making before Chain-of-Thought Generation

Fuente: arXiv

Gespeichert in:

Bibliographische Detailangaben
Hauptverfasser:	Chen, Jianan, Zhang, Zhifang, He, Shuo, Yue, Linan, Feng, Lei, Zhang, Minling
Format:	Preprint
Veröffentlicht:	2026
Schlagworte:	Artificial Intelligence
Online-Zugang:	Acceder al recurso
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Ähnliche Einträge

Training Multimodal Large Reasoning Models Needs Better Thoughts: A Three-Stage Framework for Long Chain-of-Thought Synthesis and Selection
von: Wang, Yizhi, et al.
Veröffentlicht: (2025)

SFCoT: Safer Chain-of-Thought via Active Safety Evaluation and Calibration
von: Pan, Yu, et al.
Veröffentlicht: (2026)

Bridging Efficiency and Transparency: Explainable CoT Compression in Multimodal Large Reasoning Models
von: Wang, Yizhi, et al.
Veröffentlicht: (2026)

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

Reasoning Models Struggle to Control their Chains of Thought
von: Yueh-Han, Chen, et al.
Veröffentlicht: (2026)

RAG LLMs are Not Safer: A Safety Analysis of Retrieval-Augmented Generation for Large Language Models
von: An, Bang, et al.
Veröffentlicht: (2025)

Towards Reasoning Era: A Survey of Long Chain-of-Thought for Reasoning Large Language Models
von: Chen, Qiguang, et al.
Veröffentlicht: (2025)

What Makes a Good Reasoning Chain? Uncovering Structural Patterns in Long Chain-of-Thought Reasoning
von: Jiang, Gangwei, et al.
Veröffentlicht: (2025)

Reasoning Beyond Chain-of-Thought: A Latent Computational Mode in Large Language Models
von: He, Zhenghao, et al.
Veröffentlicht: (2026)

Relevance-driven Decision Making for Safer and More Efficient Human Robot Collaboration
von: Zhang, Xiaotong, et al.
Veröffentlicht: (2024)

Interactive Reasoning: Visualizing and Controlling Chain-of-Thought Reasoning in Large Language Models
von: Pang, Rock Yuren, et al.
Veröffentlicht: (2025)

Chain-of-Thought Tokens are Computer Program Variables
von: Zhu, Fangwei, et al.
Veröffentlicht: (2025)

SafeChain: Safety of Language Models with Long Chain-of-Thought Reasoning Capabilities
von: Jiang, Fengqing, et al.
Veröffentlicht: (2025)

Stepwise Perplexity-Guided Refinement for Efficient Chain-of-Thought Reasoning in Large Language Models
von: Cui, Yingqian, et al.
Veröffentlicht: (2025)

Rethinking Reasoning Quality in Large Language Models through Enhanced Chain-of-Thought via RL
von: He, Haoyang, et al.
Veröffentlicht: (2025)

Enhancing Generalization in Chain of Thought Reasoning for Smaller Models
von: Yin, Maxwell J., et al.
Veröffentlicht: (2025)

Abstraction-of-Thought Makes Language Models Better Reasoners
von: Hong, Ruixin, et al.
Veröffentlicht: (2024)

Chain of Execution Supervision Promotes General Reasoning in Large Language Models
von: Chen, Nuo, et al.
Veröffentlicht: (2025)

Expanding Reasoning Potential in Foundation Model by Learning Diverse Chains of Thought Patterns
von: Zhang, Xuemiao, et al.
Veröffentlicht: (2025)

Pruning Long Chain-of-Thought of Large Reasoning Models via Small-Scale Preference Optimization
von: Hong, Bin, et al.
Veröffentlicht: (2025)

Multimodal Chain-of-Thought Reasoning in Language Models
von: Zhang, Zhuosheng, et al.
Veröffentlicht: (2023)

NUMCoT: Numerals and Units of Measurement in Chain-of-Thought Reasoning using Large Language Models
von: Xu, Ancheng, et al.
Veröffentlicht: (2024)

Benchmarking Multi-Step Legal Reasoning and Analyzing Chain-of-Thought Effects in Large Language Models
von: Yu, Wenhan, et al.
Veröffentlicht: (2025)

VCoT-Grasp: Grasp Foundation Models with Visual Chain-of-Thought Reasoning for Language-driven Grasp Generation
von: Zhang, Haoran, et al.
Veröffentlicht: (2025)

CoT-RAG: Integrating Chain of Thought and Retrieval-Augmented Generation to Enhance Reasoning in Large Language Models
von: Li, Feiyang, et al.
Veröffentlicht: (2025)

Policy Frameworks for Transparent Chain-of-Thought Reasoning in Large Language Models
von: Chen, Yihang, et al.
Veröffentlicht: (2025)

Unveiling Confirmation Bias in Chain-of-Thought Reasoning
von: Wan, Yue, et al.
Veröffentlicht: (2025)

Injecting Salesperson's Dialogue Strategies in Large Language Models with Chain-of-Thought Reasoning
von: Chang, Wen-Yu, et al.
Veröffentlicht: (2024)

Chain-of-Thought in Large Language Models: Decoding, Projection, and Activation
von: Yang, Hao, et al.
Veröffentlicht: (2024)

Towards Enhanced Image Generation Via Multi-modal Chain of Thought in Unified Generative Models
von: Wang, Yi, et al.
Veröffentlicht: (2025)

BadThink: Triggered Overthinking Attacks on Chain-of-Thought Reasoning in Large Language Models
von: Liu, Shuaitong, et al.
Veröffentlicht: (2025)

A Theoretical Understanding of Chain-of-Thought: Coherent Reasoning and Error-Aware Demonstration
von: Cui, Yingqian, et al.
Veröffentlicht: (2024)

Direct Value Optimization: Improving Chain-of-Thought Reasoning in LLMs with Refined Values
von: Zhang, Hongbo, et al.
Veröffentlicht: (2025)

Dynamic Chain-of-Thought: Towards Adaptive Deep Reasoning
von: Wang, Libo
Veröffentlicht: (2025)

Toward Adaptive Reasoning in Large Language Models with Thought Rollback
von: Chen, Sijia, et al.
Veröffentlicht: (2024)

Personalized Chain-of-Thought Summarization of Financial News for Investor Decision Support
von: Zhang, Tianyi, et al.
Veröffentlicht: (2025)

Diffusion of Thoughts: Chain-of-Thought Reasoning in Diffusion Language Models
von: Ye, Jiacheng, et al.
Veröffentlicht: (2024)

Diagnosing Pathological Chain-of-Thought in Reasoning Models
von: Liu, Manqing, et al.
Veröffentlicht: (2026)

Beyond Static Visual Tokens: Structured Sequential Visual Chain-of-Thought Reasoning
von: Guo, Guangfu, et al.
Veröffentlicht: (2026)

ExplainableGuard: Interpretable Adversarial Defense for Large Language Models Using Chain-of-Thought Reasoning
von: Guan, Shaowei, et al.
Veröffentlicht: (2025)