4 papers
KeyKnowledgeRAG (K^2RAG): An Enhanced RAG method for improved LLM question-answering capabilities
Hruday Markondapatnaikuni, Basem Suleiman, Abdelkarim Erradi +1
Fine-tuning is an immensely resource-intensive process when retraining Large Language Models (LLMs) to incorporate a larger body of knowledge. Although many fine-tuning techniques…
SemRAG: Semantic Knowledge-Augmented RAG for Improved Question-Answering
Kezhen Zhong, Basem Suleiman, Abdelkarim Erradi +1
This paper introduces SemRAG, an enhanced Retrieval Augmented Generation (RAG) framework that efficiently integrates domain-specific knowledge using semantic chunking and knowledge…
Enforcing Consistency and Fairness in Multi-level Hierarchical Classification with a Mask-based Output Layer
Shijing Chen, Shoaib Jameel, Mohamed Reda Bouadjenek +6
Traditional Multi-level Hierarchical Classification (MLHC) classifiers often rely on backbone models with independent output layers. This structure tends to overlook the hierar…
Leveraging Taxonomy and LLMs for Improved Multimodal Hierarchical Classification
Shijing Chen, Mohamed Reda Bouadjenek, Shoaib Jameel +5
Multi-level Hierarchical Classification (MLHC) tackles the challenge of categorizing items within a complex, multi-layered class structure. However, traditional MLHC classifiers of…