2 papers
cs.CL2025
RAGSmith: A Framework for Finding the Optimal Composition of Retrieval-Augmented Generation Methods Across Datasets
Muhammed Yusuf Kartal, Suha Kagan Kose, Korhan Sevinç +1
Retrieval-Augmented Generation (RAG) quality depends on many interacting choices across retrieval, ranking, augmentation, prompting, and generation, so optimizing modules in isolat…
cs.AI2025
A new training approach for text classification in Mental Health: LatentGLoss
Korhan Sevinç
This study presents a multi-stage approach to mental health classification by leveraging traditional machine learning algorithms, deep learning architectures, and transformer-based…