2 papers
cs.LG2026
A Sharper Picture of Generalization in Transformers
Paul Lintilhac, Sair Shaikh
We study transformers' generalization behavior on boolean domains from the perspective of the Fourier spectra of their target functions. In contrast to prior work (Edelman et al.,…
cs.AI2024
TEL'M: Test and Evaluation of Language Models
George Cybenko, Joshua Ackerman, Paul Lintilhac
Language Models have demonstrated remarkable capabilities on some tasks while failing dramatically on others. The situation has generated considerable interest in understanding and…