LLMs induce pharmacological meaning primarily from affix cues in drug names, as revealed by a framework applied to 653 drugs and localized via activation patching to early-mid layers.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CL 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
Transformers on synthetic grammar acquire abstract global statistical knowledge first, then local dependencies, showing initial over-generalizations that are later constrained.
citing papers explorer
-
What's in a Name? Morphological Shortcuts by LLMs in Pharmacology
LLMs induce pharmacological meaning primarily from affix cues in drug names, as revealed by a framework applied to 653 drugs and localized via activation patching to early-mid layers.
-
Developmental approach reveals the statistical learning of Neural Language Models: Transformers generalize from the most abstract statistical patterns
Transformers on synthetic grammar acquire abstract global statistical knowledge first, then local dependencies, showing initial over-generalizations that are later constrained.