4 papers
A Triple-Robustness Analysis of Retrieval-Augmented Generation for Multi-Hop Requirements Traceability
Meftun Akarsu, Burak Ãzdemir, DoÄancan Büyükçolak +1
Reported verdicts on GraphRAG versus vector RAG disagree, and the evidence is typically tied to a single corpus, embedder, and judge -- and, we show, to where citation quality is m…
From BM25 to Corrective RAG: Benchmarking Retrieval Strategies for Text-and-Table Documents
Meftun Akarsu, Recep Kaan Karaman, Christopher Mierbach
Retrieval-Augmented Generation (RAG) systems critically depend on retrieval quality, yet no systematic comparison of modern retrieval methods exists for heterogeneous documents con…
Code2Doc: A Quality-First Curated Dataset for Code Documentation
Recep Kaan Karaman, Meftun Akarsu
The performance of automatic code documentation generation models depends critically on the quality of the training data used for supervision. However, most existing code documenta…
RAG-Driven Data Quality Governance for Enterprise ERP Systems
Sedat Bin Vedat, Enes Kutay Yarkan, Meftun Akarsu +4
Enterprise ERP systems managing hundreds of thousands of employee records face critical data quality challenges when human resources departments perform decentralized manual entry…