Cover Image

SafeCoT: Improving VLM Safety with Minimal Reasoning

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Ma, Jiachen, Zhou, Zhanhui, Yang, Chao, Lu, Chaochao
Format:	Preprint
Published:	2025
Subjects:	Artificial Intelligence Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

RePO: Replay-Enhanced Policy Optimization
by: Li, Siheng, et al.
Published: (2025)

REFLECTOR: Internalizing Step-wise Reflection against Indirect Jailbreak
by: Ma, Jiachen, et al.
Published: (2026)

Native Reasoning Models: Training Language Models to Reason on Unverifiable Data
by: Wang, Yuanfu, et al.
Published: (2026)

Attacks, Defenses and Evaluations for LLM Conversation Safety: A Survey
by: Dong, Zhichen, et al.
Published: (2024)

Emulated Disalignment: Safety Alignment for Large Language Models May Backfire!
by: Zhou, Zhanhui, et al.
Published: (2024)

Can Post-Training Transform LLMs into Causal Reasoners?
by: Chen, Junqi, et al.
Published: (2026)

Towards AI-$45^{\circ}$ Law: A Roadmap to Trustworthy AGI
by: Yang, Chao, et al.
Published: (2024)

Self-ReSET: Learning to Self-Recover from Unsafe Reasoning Trajectories
by: Zhang, Dongcheng, et al.
Published: (2026)

Iterative Length-Regularized Direct Preference Optimization: A Case Study on Improving 7B Language Models to GPT-4 Level
by: Liu, Jie, et al.
Published: (2024)

Safety-Gymnasium: A Unified Safe Reinforcement Learning Benchmark
by: Ji, Jiaming, et al.
Published: (2023)

Beyond One-Preference-Fits-All Alignment: Multi-Objective Direct Preference Optimization
by: Zhou, Zhanhui, et al.
Published: (2023)

MAGIC: A Co-Evolving Attacker-Defender Adversarial Game for Robust LLM Safety
by: Wen, Xiaoyu, et al.
Published: (2026)

SafeMLRM: Demystifying Safety in Multi-modal Large Reasoning Models
by: Fang, Junfeng, et al.
Published: (2025)

SafeSeek: Universal Attribution of Safety Circuits in Language Models
by: Yu, Miao, et al.
Published: (2026)

Safety Mirage: How Spurious Correlations Undermine VLM Safety Fine-Tuning and Can Be Mitigated by Machine Unlearning
by: Chen, Yiwei, et al.
Published: (2025)

Weak-to-Strong Search: Align Large Language Models via Searching over Small Language Models
by: Zhou, Zhanhui, et al.
Published: (2024)

Uniformly Safe RL with Objective Suppression for Multi-Constraint Safety-Critical Applications
by: Zhou, Zihan, et al.
Published: (2024)

SafePowerGraph: Safety-aware Evaluation of Graph Neural Networks for Transmission Power Grids
by: Ghamizi, Salah, et al.
Published: (2024)

Understanding and Preserving Safety in Fine-Tuned LLMs
by: Zhang, Jiawen, et al.
Published: (2026)

Balance Reward and Safety Optimization for Safe Reinforcement Learning: A Perspective of Gradient Manipulation
by: Gu, Shangding, et al.
Published: (2024)

Learning Dynamics of VLM Finetuning
by: Zhang, Jusheng, et al.
Published: (2025)

$\mathrm{E^{2}CFD}$: Towards Effective and Efficient Cost Function Design for Safe Reinforcement Learning via Large Language Model
by: Wang, Zepeng, et al.
Published: (2024)

Sci-Reasoning: A Dataset Decoding AI Innovation Patterns
by: Liu, Jiachen, et al.
Published: (2026)

SafeSci: Safety Evaluation of Large Language Models in Science Domains and Beyond
by: Zhu, Xiangyang, et al.
Published: (2026)

VLMs Can Aggregate Scattered Training Patches
by: Zhou, Zhanhui, et al.
Published: (2025)

SafeRedirect: Defeating Internal Safety Collapse via Task-Completion Redirection in Frontier LLMs
by: Pan, Chao, et al.
Published: (2026)

GenSafe: A Generalizable Safety Enhancer for Safe Reinforcement Learning Algorithms Based on Reduced Order Markov Decision Process Model
by: Zhou, Zhehua, et al.
Published: (2024)

Safe Transformer: An Explicit Safety Bit For Interpretable And Controllable Alignment
by: Feng, Jingyuan, et al.
Published: (2026)

Safe Reinforcement Learning with Learned Non-Markovian Safety Constraints
by: Low, Siow Meng, et al.
Published: (2024)

SpatialTraceGen: High-Fidelity Traces for Efficient VLM Spatial Reasoning Distillation
by: Huh, Gio, et al.
Published: (2025)

WavefrontDiffusion: Dynamic Decoding Schedule for Improved Reasoning
by: Yang, Haojin, et al.
Published: (2025)

SafeArena: Evaluating the Safety of Autonomous Web Agents
by: Tur, Ada Defne, et al.
Published: (2025)

Reasoning as an Adaptive Defense for Safety
by: Kim, Taeyoun, et al.
Published: (2025)

LINA: Learning INterventions Adaptively for Physical Alignment and Generalization in Diffusion Models
by: Yu, Shu, et al.
Published: (2025)

Reasoning's Razor: Reasoning Improves Accuracy but Can Hurt Recall at Critical Operating Points in Safety and Hallucination Detection
by: Chegini, Atoosa, et al.
Published: (2025)

CoLD: Counterfactually-Guided Length Debiasing for Process Reward Models in Mathematical Reasoning
by: Zheng, Congmin, et al.
Published: (2025)

dLLM: Simple Diffusion Language Modeling
by: Zhou, Zhanhui, et al.
Published: (2026)

Generalizable Reasoning through Compositional Energy Minimization
by: Oarga, Alexandru, et al.
Published: (2025)

The Unreasonable Effectiveness of Entropy Minimization in LLM Reasoning
by: Agarwal, Shivam, et al.
Published: (2025)

CauScale: Neural Causal Discovery at Scale
by: Peng, Bo, et al.
Published: (2026)