Skip to content

Author

Xiaofei Wen

2 papers indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#artificial intelligence Preprint Nov 2026

MedGuardBench: A Patient-Oriented Benchmark for Personalized Guardrail Development

Using medication safety, patient-conditioned medication guarding is introduced, which predicts a safety verdict and 17 risk categories from a patient profile and prescription, and models outperform base models and matched no-profile controls in accuracy, while reducing false alarms relative to no-profile controls.

Sara Khosravi, Xiaofei Wen, M. Sarrafzadeh et al. · 0 citations

Robust and Efficient Guardrails with Latent Reasoning

Maintaining the safety of large language models (LLMs) is crucial as they are increasingly deployed in real-world applications. Existing safety guardrails typically rely on single-pass classification or, more recently, distilled reasoning. Reasoning-based guardrails significantly outperform classification-only baseline...

Siddharth Sai, Xiaofei Wen, Mu-Hao Chen · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.