Xunguang Wang
1 indexed paper
Recent (6 mo)
1With code
0Influential cites
0Benchmarked
0Publications per year
126
Top categories
AI×1Crypto×1
Frequent co-authors
Research Timeline
2026
Beyond Content Safety: Real-Time Monitoring for Reasoning Vulnerabilities in Large Language Models
This paper introduces a novel framework, the Reasoning Safety Monitor, to detect and prevent logical inconsistencies and adversarial manipulations within the internal reasoning steps of large language models, establishing reasoning safety as a critical security dimension.
Highlighted terms show continued research focus across papers
Papers
cs.AIcs.CRRecentMar 26, 2026
Beyond Content Safety: Real-Time Monitoring for Reasoning Vulnerabilities in Large Language Models
Xunguang Wang, Yuguang Zhou, Qingyue Wang, Zongjie Li +4 more
This paper introduces a novel framework, the Reasoning Safety Monitor, to detect and prevent logical inconsistencies and adversarial manipulations within the internal reasoning steps of large language…
View →