No Resource, No Benchmarks, No Problem? Evaluating and Improving LLMs for Code Generation in No-Resource Languages
Research addresses code generation challenges for no-resource programming languages by developing benchmarks and proposing a method that combines further pre-training with weight d…
Hugging Face · Daily Papers
·Alessandro Giagnorio, Alberto Martin-Lopez
·
·▲ 3 upvotes
Este artigo está em destaque na seleção diária de papers do Hugging Face, curada pela comunidade de pesquisa em IA.
Autores: Alessandro Giagnorio, Alberto Martin-Lopez, Gabriele Bavota
- 3 upvotes da comunidade
- Temas: large language models, code generation, no-resource languages, prompt-based techniques, pre-training, fine-tuning
Resumo
Resumo original (em inglês), extraído do paper:
Research addresses code generation challenges for no-resource programming languages by developing benchmarks and proposing a method that combines further pre-training with weight difference transfer to create specialized instruction-following models at reduced computational cost.
// relacionados
Leia também
Blog
How Businesses Are Building Specialized AI They Can Trust
Blog
Fika Jobs raises $4M to build a video-first hiring platform where AI agents interview candidates
Blog
Build real agentic apps using CUGA: two dozen working examples on a lightweight harness
Blog