Decoding Compressed Trust: Scrutinizing the Trustworthiness of Efficient LLMs Under Compression

no code implementations • 18 Mar 2024 • Junyuan Hong, Jinhao Duan, Chenhui Zhang, Zhangheng Li, Chulin Xie, Kelsey Lieberman, James Diffenderfer, Brian Bartoldson, Ajay Jaiswal, Kaidi Xu, Bhavya Kailkhura, Dan Hendrycks, Dawn Song, Zhangyang Wang, Bo Li

While state-of-the-art (SoTA) compression methods boast impressive advancements in preserving benign task performance, the potential risks of compression in terms of safety and trustworthiness have been largely neglected.

Ethics Fairness +1

Latent Space Simulation for Carbon Capture Design Optimization

1 code implementation • 22 Dec 2021 • Brian Bartoldson, Rui Wang, Yucheng Fu, David Widemann, Sam Nguyen, Jie Bao, Zhijie Xu, Brenda Ng

This raises the possibility of a fast, accurate replacement for a CFD simulator and therefore efficient approximation of the IAs required by CCS design optimization.

Enhancing the Regularization Effect of Weight Pruning in Artificial Neural Networks

no code implementations • 4 May 2018 • Brian Bartoldson, Adrian Barbu, Gordon Erlebacher

Removing weights from an ANN is a form of regularization, but existing pruning algorithms do not significantly improve generalization error.

General Classification Image Classification