← Search

Matvey Mikhalchuk

2 accepted papers

2025

LLM-Microscope: Uncovering the Hidden Role of Punctuation in Context Memory of Transformers

NAACL 2025findings

We introduce methods to quantify how Large Language Models (LLMs) encode and store contextual information, revealing that tokens often seen as minor (e.g., determiners, punctuation) carry surprisingly high context. Notably, removing these tokens — especially stopwords, articles, and commas — consist…

Cited by 1SourcePDFScholar
2024

Your Transformer is Secretly Linear

ACL 2024long

This paper reveals a novel linear characteristic exclusive to transformer decoders, including models like GPT, LLaMA, OPT, BLOOM and others. We analyze embedding transformations between sequential layers, uncovering an almost perfect linear relationship (Procrustes similarity score of 0.99). However…