Skip to content
Sagan

Paper

The Geometry of Updates: Fisher Alignment at Vocabulary Scale

Unreadunread

AI summary

arXiv:2606. 27242v1 Announce Type: cross Abstract: Training-free source selection for LLM families with shared vocabularies arises in scientific string domains such as SMILES, protein, and genomic sequences, where candidate corpora share a tokenizer but differ in prediction targets.