Cover Image

SafeRBench: Dissecting the Reasoning Safety of Large Language Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Gao, Xin, Yu, Shaohan, Chen, Zerui, Lyu, Yueming, Yu, Weichen, Li, Guanghao, Liu, Jiyao, Gao, Jianxiong, Liang, Jian, Liu, Ziwei, Si, Chenyang
Format:	Preprint
Published:	2025
Subjects:	Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

GOOD: Training-Free Guided Diffusion Sampling for Out-of-Distribution Detection
by: Gao, Xin, et al.
Published: (2025)

LongVie: Multimodal-Guided Controllable Ultra-Long Video Generation
by: Gao, Jianxiong, et al.
Published: (2025)

RepVideo: Rethinking Cross-Layer Representation for Video Generation
by: Si, Chenyang, et al.
Published: (2025)

Dissecting Failure Dynamics in Large Language Model Reasoning
by: Zhu, Wei, et al.
Published: (2026)

LongVie 2: Multimodal Controllable Ultra-Long Video World Model
by: Gao, Jianxiong, et al.
Published: (2025)

$\texttt{MoE-RBench}$: Towards Building Reliable Language Models with Sparse Mixture-of-Experts
by: Chen, Guanjie, et al.
Published: (2024)

When the Same Coefficients Reach Different Places: Asymmetric Realizability in Transplanting Tokenizers across Large Language Models
by: Liu, Xiaoze, et al.
Published: (2025)

RBench-V: A Primary Assessment for Visual Reasoning Models with Multi-modal Outputs
by: Guo, Meng-Hao, et al.
Published: (2025)

Reasoning on the Manifold: Bidirectional Consistency for Self-Verification in Diffusion Language Models
by: Ruan, Jiaoyang, et al.
Published: (2026)

Spatial Reasoning in Multimodal Large Language Models: A Survey of Tasks, Benchmarks and Methods
by: Liu, Weichen, et al.
Published: (2025)

ProGuard: Towards Proactive Multimodal Safeguard
by: Yu, Shaohan, et al.
Published: (2025)

A2RBench: An Automatic Paradigm for Formally Verifiable Abstract Reasoning Benchmark Generation
by: Ma, Qingchuan, et al.
Published: (2026)

CoSafe: Evaluating Large Language Model Safety in Multi-Turn Dialogue Coreference
by: Yu, Erxin, et al.
Published: (2024)

SafeVid: Toward Safety Aligned Video Large Multimodal Models
by: Wang, Yixu, et al.
Published: (2025)

Safe Semantics, Unsafe Interpretations: Tackling Implicit Reasoning Safety in Large Vision-Language Models
by: Cai, Wei, et al.
Published: (2025)

SafeBench: A Safety Evaluation Framework for Multimodal Large Language Models
by: Ying, Zonghao, et al.
Published: (2024)

MosaicThinker: On-Device Visual Spatial Reasoning for Embodied AI via Iterative Construction of Space Representation
by: Wang, Haoming, et al.
Published: (2026)

Retrieval-augmented Multi-modal Chain-of-Thoughts Reasoning for Large Language Models
by: Liu, Bingshuai, et al.
Published: (2023)

YouthSafe: A Youth-Centric Safety Benchmark and Safeguard Model for Large Language Models
by: Yu, Yaman, et al.
Published: (2025)

LSSF: Safety Alignment for Large Language Models through Low-Rank Safety Subspace Fusion
by: Zhou, Guanghao, et al.
Published: (2026)

When Safe Unimodal Inputs Collide: Optimizing Reasoning Chains for Cross-Modal Safety in Multimodal Large Language Models
by: Cai, Wei, et al.
Published: (2025)

FreeMorph: Tuning-Free Generalized Image Morphing with Diffusion Model
by: Cao, Yukang, et al.
Published: (2025)

HG3-NeRF: Hierarchical Geometric, Semantic, and Photometric Guided Neural Radiance Fields for Sparse View Inputs
by: Gao, Zelin, et al.
Published: (2024)

Divide and Conquer: Accelerating Diffusion-Based Large Language Models via Adaptive Parallel Decoding
by: Luo, Xiangzhong, et al.
Published: (2026)

Dynamic Residual Safe Reinforcement Learning for Multi-Agent Safety-Critical Scenarios Decision-Making
by: Wang, Kaifeng, et al.
Published: (2025)

SafeKey: Amplifying Aha-Moment Insights for Safety Reasoning
by: Zhou, Kaiwen, et al.
Published: (2025)

Safety of Multimodal Large Language Models on Images and Texts
by: Liu, Xin, et al.
Published: (2024)

ETSM: Automating Dissection Trajectory Suggestion and Confidence Map-Based Safety Margin Prediction for Robot-assisted Endoscopic Submucosal Dissection
by: Xu, Mengya, et al.
Published: (2024)

Open3D-VQA: A Benchmark for Comprehensive Spatial Reasoning with Multimodal Large Language Model in Open Space
by: Zhang, Weichen, et al.
Published: (2025)

A Comprehensive Survey on Trustworthiness in Reasoning with Large Language Models
by: Wang, Yanbo, et al.
Published: (2025)

Dark-ISP: Enhancing RAW Image Processing for Low-Light Object Detection
by: Guo, Jiasheng, et al.
Published: (2025)

ChineseSafe: A Chinese Benchmark for Evaluating Safety in Large Language Models
by: Zhang, Hengxiang, et al.
Published: (2024)

Performance Enhancement for Adaptive Safe Control Systems Tracking Periodic Signals
by: Lijun Liu, et al.
Published: (2025)

MM-SafetyBench: A Benchmark for Safety Evaluation of Multimodal Large Language Models
by: Liu, Xin, et al.
Published: (2023)

Reasoning Path and Latent State Analysis for Multi-view Visual Spatial Reasoning: A Cognitive Science Perspective
by: Xue, Qiyao, et al.
Published: (2025)

Route-and-Reason: Scaling Large Language Model Reasoning with Reinforced Model Router
by: Shao, Chenyang, et al.
Published: (2025)

Reinforced MLLM: A Survey on RL-Based Reasoning in Multimodal Large Language Models
by: Zhou, Guanghao, et al.
Published: (2025)

THE-Tree: Can Tracing Historical Evolution Enhance Scientific Verification and Reasoning?
by: Wang, Xin, et al.
Published: (2025)

Comment on “The Efficacy and Safety of Endoscopic Submucosal Dissection (ESD) Combined With Radiofrequency Ablation (RFA) Sequential Therapy for Extensive Esophageal Lesions”
by: Jing‐Yu Zhu, et al.
Published: (2025)

UpSafe$^\circ$C: Upcycling for Controllable Safety in Large Language Models
by: Sun, Yuhao, et al.
Published: (2025)