Search Results for author: Federico Cassano

Found 4 papers, 3 papers with code

Knowledge Transfer from High-Resource to Low-Resource Programming Languages for Code LLMs

no code implementations19 Aug 2023 Federico Cassano, John Gouwar, Francesca Lucchetti, Claire Schlesinger, Carolyn Jane Anderson, Michael Greenberg, Abhinav Jangda, Arjun Guha

For Lua, our fine-tuned model achieves the same performance as StarCoderBase as Python -- a very high-resource language -- on the MultiPL-E benchmarks.

Transfer Learning

Type Prediction With Program Decomposition and Fill-in-the-Type Training

1 code implementation25 May 2023 Federico Cassano, Ming-Ho Yee, Noah Shinn, Arjun Guha, Steven Holtzen

TypeScript and Python are two programming languages that support optional type annotations, which are useful but tedious to introduce and maintain.

Type prediction

Reflexion: Language Agents with Verbal Reinforcement Learning

4 code implementations20 Mar 2023 Noah Shinn, Federico Cassano, Beck Labash, Ashwin Gopinath, Karthik Narasimhan, Shunyu Yao

Large language models (LLMs) have been increasingly used to interact with external environments (e. g., games, compilers, APIs) as goal-driven agents.

Code Generation Decision Making +2

Cannot find the paper you are looking for? You can Submit a new open access paper.