Get started
Author

Bowen Wei

Observed name: Wei, Bowen
Observed institution: George Mason University
OpenAlex ID: A5129711177
ClawSafety: "Safe" LLMs, Unsafe Agents
2026 · Wei, Bowen, Zhang, Yunbei, et al. · arXiv (Cornell University) · 25
PDF
Making Sense of LLM Decisions: A Prototype-based Framework for Explainable Classification
2026 · Bowen Wei, Mehrdad Fazli, et al. · Proceedings of the AAAI Conference on Artificial Intelligence · 1
PDF
Knowing Bias, Doing Better: Mitigating Social Bias in LLMs via Know-Bias Neuron Enhancement
2026 · Pan, Jinhao, Raj, Chahat, et al. · arXiv (Cornell University) · 1
PDF
Learning from Self-Generated Responses: Reliability--Uncertainty Self-Distillation for Reasoning
2026 · Pan, Jinhao, Wei, Bowen, et al. · arXiv (Cornell University)
PDF
VIGNETTE: Socially Grounded Bias Evaluation for Vision-Language Models
2026 · Association for Computational Linguistics 2026, Anastasopoulos, Antonios, et al. · Underline Science Inc.
Inject to Heal: Alleviating hallucination in LVLMs via Context Embedding Injection
2026 · Association for Computational Linguistics 2026, Fazli, Mehrdad, et al. · Underline Science Inc.
A Logical-Rule Autoencoder for Interpretable Recommendations
2026 · Pan, Jinhao, Wei, Bowen, et al. · arXiv (Cornell University)
PDF
Making Sense of LLM Decisions: A Prototype-based Framework for Explainable Classification
2026 · Association for Artificial Intelligence 2026, Fazli, Mehrdad, et al. · Underline Science Inc.
COSE: Confidence-Orchestrated Self-Evolution for Effective LLM Reasoning
2026 · Bowen Wei, Nan Wang, et al. · Conference on Empirical Methods in Natural Language Processing (EMNLP)
PDF
Works count: 9
Citation count: 27
H-index: 1
I10-index: 1
Year
Topic
Type