Author

Yibo Hu

Observed name: Hu, Yibo

Institution: Illinois Institute of Technology

Observed institution: Illinois Institute of Technology

OpenAlex ID: A5137882511

Easier to Mislead Than to Correct: Harmful and Beneficial Revision in LLM Conformity

2026 · Qu, Jiaming, Fu, Lucheng, et al. · arXiv (Cornell University) · 1

Conformity Breaks Conformal Prediction

2026 · Hu, Yibo, Su, Hanyu · arXiv (Cornell University)

Safety-Flag: A Unified Benchmark for the Reliability and Calibration of LLM Content Moderators

2026 · Hu, Yibo · arXiv (Cornell University)

Social Pressure Breaks Majority Voting in LLM Safety Panels

2026 · Hu, Yibo, Qu, Jiaming · arXiv (Cornell University)

The Evaluator Is Part of the Experiment: Measuring Open-Ended LLM Conformity

2026 · Guerra, Alicia, Hu, Yibo · arXiv (Cornell University)

Subtype Robustness Is Not Just Accuracy: Calibration Under Unseen Subtype Shift

2026 · Su, Hanyu, Juanola, Carlota Julbe i, et al. · arXiv (Cornell University)

Early Detection of Distributed Backdoors in Multi-Agent LLM Systems: A Characterization Study

2026 · Arias, Diego Fernandez, Mistry, Dev Prashant, et al. · arXiv (Cornell University)

When Local Monitors Miss Compositional Harm: Diagnosing Distributed Backdoors in Multi-Agent Systems

2026 · Hu, Yibo, Wang, Ren · arXiv (Cornell University)

Most LLM Conformity Needs No Speaker: Measuring the Speaker-Free Floor in Peer-Pressure Benchmarks

2026 · Hu, Yibo, Qu, Jiaming · arXiv (Cornell University)

When Surface Form Changes Moderation Decisions: A Paired Study of Code-Mixed Workflow Instability

2026 · Krishnaram, Suraj Babu Thimma, Hu, Yibo, et al. · arXiv (Cornell University)

Works count: 10

Citation count: 1

H-index: 1

I10-index: