Xuchan Bao

4

Papers

163

Total Citations

Papers (4)

Emergent Misalignment: Narrow finetuning can produce broadly misaligned LLMs

Tell me about yourself: LLMs are aware of their learned behaviors

Regularized linear autoencoders recover the principal components, eventually

NeurIPS 2020arXiv

Learning to Elect

NeurIPS 2021arXiv