2 papers
cs.CL2026
Mecellem Models: Turkish Models Trained from Scratch and Continually Pre-trained for the Legal Domain
Özgür Uğur, Mahmut Göksu, Mahmut Çimen +6
This paper presents Mecellem models, a framework for developing specialized language models for the Turkish legal domain through domain adaptation strategies. We make two contribut…
cs.CL2025
Guided Decoding and Its Critical Role in Retrieval-Augmented Generation
Özgür Uğur, Musa Yılmaz, Esra Şavirdi +4
The integration of Large Language Models (LLMs) into various applications has driven the need for structured and reliable responses. A key challenge in Retrieval-Augmented Generati…