@article{dharmaocrspecializedsmalllanguagemodelsf, title = {DharmaOCR: Specialized Small Language Models for Structured OCR that outperform Open-Source and Commercial Baselines}, author = {Gabriel Pimenta de Freitas Cardoso and Caio Lucas da Silva Chacon and Jonas Felipe da Fonseca Oliveira and Paulo Henrique de Medeiros Araujo}, year = {2026}, eprint = {2604.14314}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2604.14314}, }