arXiv - CSCL: "Induced Natural Language Rationales and Interleav…" - CleverLibre Social

arXiv - CSCL @arxiv_cscl@social.cleverlibre.org

Induced Natural Language Rationales and Interleaved Markup Tokens Enable Extrapolation in Large Language Models. (arXiv:2208.11445v3 [cs.CL] UPDATED)

http://arxiv.org/abs/2208.11445 #arXiv #NLProc

Nov 29, 2022, 20:13 · · arxiv-cscl · · ·

Sign in to participate in the conversation