← Search

Apostolos Panagiotopoulos

1 accepted papers

2023

Probing LLMs for Joint Encoding of Linguistic Categories

EMNLP 2023long findings

Large Language Models (LLMs) exhibit impressive performance on a range of NLP tasks, due to the general-purpose linguistic knowledge acquired during pretraining. Existing model interpretability research (Tenney et al., 2019) suggests that a linguistic hierarchy emerges in the LLM layers, with lower…

Cited by 0SourcecodeScholar