arXiv - CSCL: "Transformer-Based Models Are Not Yet Perfect At L…" - CleverLibre Social

arXiv - CSCL @arxiv_cscl@social.cleverlibre.org

Transformer-Based Models Are Not Yet Perfect At Learning to Emulate Structural Recursion. (arXiv:2401.12947v1 [cs.CL])

http://arxiv.org/abs/2401.12947 #arXiv #NLProc

Jan 24, 2024, 03:19 · · arxiv-cscl · · ·

Sign in to participate in the conversation