News for hackers. Stuff that matters.

A comment on Type-constrained code generation with language models.

Re:Type-constrained code generation with language models by slt2021 on Tuesday May 13, 2025 @08:23PM (#43979402)
we really need LLM trained on AST, instead of token, is there any research on this?
[ Parent | on HN ]
Re:Type-constrained code generation with language models by tough on Tuesday May 13, 2025 @08:30PM (#43979443)
ASTrust: Towards More Trustworthy and Interpretable LLMs for Code through Syntax-Grounded Explanations

https://arxiv.org/abs/2407.08983

AST-T5: Structure-Aware Pretraining for Code Generation and Understanding

https://arxiv.org/abs/2401.03003

CodeGRAG: Bridging the Gap between Natural Language and Programming Language via Graphical Retrieval Augmented Generation

https://arxiv.org/abs/2405.02355

[ Parent | on HN ]
Re:Type-constrained code generation with language models by nielstron on Wednesday May 14, 2025 @02:10AM (#43981362)
The downside is that you need to properly preprocess code, have less non-code Training Data, and can not adapt easily to new programming languages
[ Parent | on HN ]