04/04/25: Constrained Decoding for Code Language Models via Efficient Left and Right Quotienting of Context-Sensitive Grammars with Daniel Melcer

0:00-58:33

Today Daniel Melcer joined us to present Constrained Decoding for Code Language Models via Efficient Left and Right Quotienting of Context-Sensitive Grammars (https://arxiv.org/pdf/2402.17988). This is work he completed while at Amazon, and it's a really interesting project around how to constrain, guide, and check language models such that they generate valid code within a given context. We really appreciate that Daniel took the time to talk to us and hope you like the talk as much as we did!

Publisher

Boston Computation Club

Link

podcasters.spotify.com/pod/show/bostoncc/episodes/040425-Constrained-Decoding-for-Code-Language-Models-via-Efficient-Left-and-Right-Quotienting-of-Context-Sensitive-Grammars-with-Daniel-Melcer-e3157l0

Published

April 5, 2025

Duration

59 min

Format

Podcast

Category

Issues · Science

Source

RSS feed

Host

Max von Hippel

BC

Boston Computation Club

@bostoncomputationclub

#constraineddecoding #codelanguagemodels #sensitivegrammars #mathematics

The Nile