Search papers, labs, and topics across Lattice.
4
0
6
4
Pharo-specialized LLMs achieve superior code completion accuracy, outperforming larger models and paving the way for robust support in low-resource programming languages.
No-resource languages can achieve significant code generation improvements through a novel pre-training and instruction-following hybrid approach, challenging conventional training paradigms.
Forget expensive LLMs: modern small language models can judge code correctness well enough to rival the code generation performance of models 5-25x larger.
Despite generating 2.4x more suggestions, ChatGPT-4 misses 90% of the quality issues spotted by human code reviewers, highlighting the limitations of current DL-based code review automation.
