[wrs]

Is there evidence that modern LLMs identify parts of speech in an observable way? This explanation sounds more like how we did it in the 90s before deep learning took over.

[Xmd5a]

https://arxiv.org/abs/1906.04341

https://arxiv.org/abs/1905.05950

https://en.wikiversity.org/wiki/Psycholinguistics/Models_of_...