Author

George Wang

Observed name: Wang, George

OpenAlex ID: A5123528005

Patterning in Practice: Debiasing Reward Models with Susceptibilities

2026 · Wang, George, Donoway, Elizabeth, et al. · arXiv (Cornell University)

Patterning: The Dual of Interpretability

2026 · Wang, George, Murfet, Daniel · arXiv (Cornell University)

Towards Spectroscopy: Susceptibility Clusters in Language Models

2026 · Gordon, Andrew, Baker, Garrett, et al. · arXiv (Cornell University)

Works count: 3

Citation count:

H-index:

I10-index: