cosql

Papers using or citing this model 1

• PICARD: Parsing Incrementally for Constrained Auto-Regressive Decoding from Language Models 759 citations · 2021 · Conference on Empirical Methods in Natural Language Processing · arXiv

  Large pre-trained language models for textual data have an unconstrained output space; at each decoding step, they can produce any of 10,000s of sub-word tokens. When fine-tuned to target constrained formal languages like SQL, these...