December 02, 2022
This paper investigates the failure cases and out-of-distribution behavior of trans- formers trained on matrix inversion and eigenvalue decomposition. I show that incorrect model predictions still retain deep mathematical properties of the solution (e.g. correct eigenvalues, unit norm of eigenvectors), and that almost all model fail- ures can be attributed to, and predicted from, properties of the problem or solution. This demonstrates that, when in doubt, math transformers do not hallucinate absurd solutions (as was sometimes proposed) but remain “roughly right”. I also show that the careful choice of a training dataset can accelerate training, while allowing the model to generalize out of its training distribution, invalidating the idea that transformers “merely interpolate” from memorized examples.
Written by
François Charton
Publisher
Neurips MAH-AI workshop
September 05, 2024
Chunting Zhou, Lili Yu, Arun Babu, Kushal Tirumala, Michihiro Yasunaga, Leonid Shamis, Jacob Kahn, Luke Zettlemoyer, Omer Levy, Xuezhe Ma
September 05, 2024
August 20, 2024
Ashish Shenoy, Yichao Lu, Srihari Jayakumar, Debojeet Chatterjee, Mohsen Moslehpour, Pierce Chuang, Abhay Harpale, Vikas Bhardwaj, Di Xu (SWE), Shicong Zhao, Ankit Ramchandani, Luna Dong, Anuj Kumar
August 20, 2024
August 12, 2024
Arman Zharmagambetov, Yuandong Tian, Aaron Ferber, Bistra Dilkina, Taoan Huang
August 12, 2024
August 11, 2024
Igor Tufanov, Karen Hambardzumyan, Javier Ferrando, Lena Voita
August 11, 2024
Foundational models
Latest news
Foundational models