As to the training set's depth of APL, yes, it's an issue. However, it's worth seeing how well MoonBit[1, 2] works with LLMs, faced with exactly the same problem -- integrating the LLM directly into the parser pipeline.

1: https://www.youtube.com/watch?v=SnY0F9w1xdM 2: https://www.moonbitlang.com/blog/moonbit-ai