Institution profile

Roketsan Roket Sanayii ve Ticaret AS

Industry researcheurope · tr
Official website
Research library1linked papers
Opportunities0open roles
Selected work

Representative Papers

RAGSmith: A Framework for Finding the Optimal Composition of Retrieval-Augmented Generation Methods Across Datasets

Nov 03, 2025

Traditional RAG systems suffer from suboptimal performance due to tight coupling among retrieval, reranking, prompt rewriting, and generation modules, hindering holistic optimization. Method: This paper proposes the first end-to-end RAG architecture search framework, modeling the RAG configuration space as an evolvable search problem and employing genetic algorithms to jointly optimize multi-objective metrics—including recall@k/nDCG for retrieval and LLM-Judge/semantic similarity for generation. The framework encompasses nine component types across vector retrieval, reranking, and prompt rewriting. Contribution/Results: Evaluated across six domains, the framework achieves an average 3.8% performance gain (up to +12.5% in retrieval, +7.5% in generation) while converging after exploring only 0.2% of the configuration space. It identifies robust architectural patterns transferable across datasets and quantifies how domain characteristics and question types systematically influence optimal configurations.

0 citationsRead paper
Recent publications

Latest Papers

RAGSmith: A Framework for Finding the Optimal Composition of Retrieval-Augmented Generation Methods Across Datasets

Nov 03, 2025

Traditional RAG systems suffer from suboptimal performance due to tight coupling among retrieval, reranking, prompt rewriting, and generation modules, hindering holistic optimization. Method: This paper proposes the first end-to-end RAG architecture search framework, modeling the RAG configuration space as an evolvable search problem and employing genetic algorithms to jointly optimize multi-objective metrics—including recall@k/nDCG for retrieval and LLM-Judge/semantic similarity for generation. The framework encompasses nine component types across vector retrieval, reranking, and prompt rewriting. Contribution/Results: Evaluated across six domains, the framework achieves an average 3.8% performance gain (up to +12.5% in retrieval, +7.5% in generation) while converging after exploring only 0.2% of the configuration space. It identifies robust architectural patterns transferable across datasets and quantifies how domain characteristics and question types systematically influence optimal configurations.

0 citationsRead paper