Sy-Tuyen Ho

hosytuyen

·

https://hosytuyen.github.io

AI & ML interests

Data Protection and Reliable AI

Recent Activity

authored a paper about 17 hours ago

When AI Reviews Train AI Reviewers: Scientific-Judgment Collapse and Mitigation

authored a paper about 17 hours ago

Bias in the Tails: How Name-conditioned Evaluative Framing in Resume Summaries Destabilizes LLM-based Hiring

authored a paper about 17 hours ago

Trait-space Monitoring for Emergent Misalignment During Supervised Finetuning

View all activity

Organizations

hosytuyen 's papers 10

arxiv:2609.20942

arxiv:2606.07631

arxiv:2605.30329

arxiv:2604.19984

arxiv:2603.08706

arxiv:2508.04097

arxiv:2505.03519

arxiv:2501.03782

arxiv:2409.01696

arxiv:2405.05588