no code implementations • 14 Apr 2023 • Swapnil Sharma, Nikita Anand, Kranthi Kiran G. V
Large language models pre-trained for code generation can generate high-quality short code but often struggle with generating coherent long code and understanding higher-level or system-level specifications.
no code implementations • 13 Apr 2023 • Swapnil Sharma, Nikita Anand, Kranthi Kiran G. V., Alind Jain
The results are compiled and we find that all the models under study do exhibit biases but have generally improved as compared to BERT.