Built with and by Teycir Ben Soltane•
How to Use•FAQ•GitHub•arXiv.org•
Share:
ArXivCSExplorer
☆☆Bookmarks🏆RSSHow to UseFAQ
Home/Authors/Xiaofei Wen

Xiaofei Wen

5 indexed papers

Recent (6 mo)
5
With code
0
Influential cites
0
Benchmarked
0

Publications per year

5
26

Top categories

Crypto×5NLP×4AI×2ML×2

Frequent co-authors

Muhao Chen5×
Wenjie Jacky Mo2×
Rui Cai2×
Boyu Zhu2×
Sicong Jiang2×
Zihan Wang2×

Research Timeline

2026
Cooking Up Risks: Benchmarking and Reducing Food Safety Risks in Large Language Models

The paper introduces FoodGuardBench, a comprehensive benchmark and a specialized guardrail model (FoodGuard-4B) to rigorously test and mitigate the severe food safety risks posed by large language models.

Robust and Efficient Guardrails with Latent Reasoning

The paper introduces COLAGUARD, a novel guardrail model that efficiently transfers multi-step safety reasoning into a continuous latent space, achieving high safety performance with massive improvements in speed and token efficiency compared to existing methods.

Robust and Efficient Guardrails with Latent Reasoning

The paper introduces COLAGUARD, a novel guardrail model that efficiently transfers multi-step safety reasoning into a continuous latent space, achieving state-of-the-art safety performance with massive improvements in inference speed and efficiency.

Triaging Threats to Specialized Guardrails

The paper introduces RouteGuard, a router-expert framework, to improve the robustness and generalization of safety guardrails by specializing threat detection across multiple distinct unsafe categories.

Triaging Threats to Specialized Guardrails

The paper introduces RouteGuard, a router-expert framework, to improve the robustness and generalization of safety guardrails by specializing threat detection across multiple unsafe categories.

Highlighted terms show continued research focus across papers

Papers

cs.CRcs.CLRecentMay 29, 2026

Triaging Threats to Specialized Guardrails

Wenjie Jacky Mo, Xiaofei Wen, Rui Cai, Boyu Zhu +5 more

The paper introduces RouteGuard, a router-expert framework, to improve the robustness and generalization of safety guardrails by specializing threat detection across multiple distinct unsafe categorie…

View →
cs.CRcs.CLRecentMay 29, 2026

Triaging Threats to Specialized Guardrails

Wenjie Jacky Mo, Xiaofei Wen, Rui Cai, Boyu Zhu +5 more

The paper introduces RouteGuard, a router-expert framework, to improve the robustness and generalization of safety guardrails by specializing threat detection across multiple unsafe categories.

View →
cs.AIcs.CLcs.CRRecentMay 27, 2026

Robust and Efficient Guardrails with Latent Reasoning

Siddharth Sai, Xiaofei Wen, Muhao Chen

The paper introduces COLAGUARD, a novel guardrail model that efficiently transfers multi-step safety reasoning into a continuous latent space, achieving high safety performance with massive improvemen…

View →
cs.AIcs.CLcs.CRRecentMay 27, 2026

Robust and Efficient Guardrails with Latent Reasoning

Siddharth Sai, Xiaofei Wen, Muhao Chen

The paper introduces COLAGUARD, a novel guardrail model that efficiently transfers multi-step safety reasoning into a continuous latent space, achieving state-of-the-art safety performance with massiv…

View →
cs.CRRecentApr 1, 2026

Cooking Up Risks: Benchmarking and Reducing Food Safety Risks in Large Language Models

Weidi Luo, Xiaofei Wen, Tenghao Huang, Hongyi Wang +4 more

The paper introduces FoodGuardBench, a comprehensive benchmark and a specialized guardrail model (FoodGuard-4B) to rigorously test and mitigate the severe food safety risks posed by large language mod…

View →