← Search

Paul Lerner

2 accepted papers

2025

Unlike “Likely”, “Unlike” is Unlikely: BPE-based Segmentation hurts Morphological Derivations in LLMs

COLING 2025main

Large Language Models (LLMs) rely on subword vocabularies to process and generate text. However, because subwords are marked as initial- or intra-word, we find that LLMs perform poorly at handling some types of affixations, which hinders their ability to generate novel (unobserved) word forms. The l…