The transition from dense to sparse model architectures has become a key trend in the field of Large Language Models (LLMs). Mixture-of-Experts (MoE) methods can be used to increase model conditional representation capacity by activating only a subset of parameters for each input token. However, the practical efficienc...
This study proposes a two-stage training framework that integrates Supervised Fine-Tuning (SFT) and Direct Preference Optimization (DPO) within a unified data construction pipeline and provides a reproducible pathway to develop reliable multimodal systems that deliver auditable, actionable disaster insights for emergen...
A ReliefWeb study (2000-2024) and a two-stage Large Language Model (LLM) pipeline that extracts structured intervention-outcome records with direction and strength attributes and proposes context-preserving triangulation that aggregates strength-weighted evidence within disaster cells.
Yuanjun Zhang, Mourad Oussalah· Annual Meeting of the Associ...· 0 citations
This work introduces MedFaith-F1, a category-level faithfulness metric over four clinically salient categories: clinical problems, medications, procedures, and follow-up intent, and proposes a hybrid Evidence and Knowledge-Grounded Retrieval-Augmented Generation ( EKG-RAG), an evidence and knowledge-grounded framework...
Md Rabiul Hasan, Aleka Melese Ayalew, Mourad Oussalah· Proceedings of the 11th Soci...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
