AI safety researcher

Chenhao Tan

Google Scholar dblp

Last 12 months5 papers

Analysis and theory 1Risky behavior 1

AI safety papers from the last year

On this site: 9 papers

August 2026

Emergent Misalignment Is Not Magical
Aug 29Analysis and theoryarXiv ↗

July 2026

Characterizing Rhetorical Misalignment in Decision-Making with Language Models
Jul 24Risky behaviorarXiv ↗

June 2026

Collaborative Disagreement Resolution for Scalable Oversight
Jun 2arXiv ↗

May 2026

Iterative Finetuning is Mostly Idempotent
May 1arXiv ↗

April 2026

Keeping an Eye on AI: A Framework for Effective Human Oversight of AI Systems
Apr 9arXiv ↗

Authorship follows dblp and the author's own Google Scholar profile; only AI safety papers on this site are listed.