Follow-up Attention: An Empirical Study of Developer and Neural Model Code Exploration

Understand

Recent neural models of code, such as OpenAI Codex and AlphaCode, have demonstrated remarkable proficiency at code generation due to the underlying attention mechanism.

• However, it often remains unclear how the models actually process code, and to what extent their reasoning and the way their attention mechanism scans the code matches the patterns of developers.
• A poor understanding of the model reasoning process limits the way in which current neural models are leveraged today, so far mostly for their raw prediction.
• To fill this gap, this work studies how the processed attention signal of three open large language models - CodeGen, InCoder and GPT-J - agrees with how developers look at and explore code when each answers the same sensemaking questions about code.