
04/04/25: Constrained Decoding for Code Language Models via Efficient Left and Right Quotienting of Context-Sensitive Grammars with Daniel Melcer
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
Boston Computation Club
@bostoncomputationclub
#constraineddecoding #codelanguagemodels #sensitivegrammars #mathematics
