3 papers
cs.AI2025
AuditAgent: Expert-Guided Multi-Agent Reasoning for Cross-Document Fraudulent Evidence Discovery
Songran Bai, Bingzhe Wu, Yiwei Zhang +5
Financial fraud detection in real-world scenarios presents significant challenges due to the subtlety and dispersion of evidence across complex, multi-year financial disclosures. I…
cs.LG2025
SAFEx: Analyzing Vulnerabilities of MoE-Based LLMs via Stable Safety-critical Expert Identification
Zhenglin Lai, Mengyao Liao, Bingzhe Wu +5
Large language models with Mixture-of-Experts (MoE) architectures achieve efficiency and scalability, yet their routing mechanisms introduce safety alignment challenges insufficien…
cs.LG2025
Sparsification and Reconstruction from the Perspective of Representation Geometry
Wenjie Sun, Bingzhe Wu, Zhile Yang +1
Sparse Autoencoders (SAEs) have emerged as a predominant tool in mechanistic interpretability, aiming to identify interpretable monosemantic features. However, how does sparse enco…