by Chris Potts Papers
3 papers found
Conference
Blackbox Model Provenance via Palimpsestic Membership Inference
Rohith Kuditipudi, Jing Huang, Sally Zhu et al.
NEURIPS 2025spotlightarXiv:2510.19796
2
citations
Do Language Models Use Their Depth Efficiently?
Róbert Csordás, Christopher D Manning, Chris Potts
NEURIPS 2025arXiv:2505.13898
21
citations
Improved Representation Steering for Language Models
Zhengxuan Wu, Qinan Yu, Aryaman Arora et al.
NEURIPS 2025spotlightarXiv:2505.20809
6
citations