FUSE-RAG: A Unified Architecture for Retrieval-Augmented Generation FUSE-RAG: Getirim Destekli Üretim için Bütüncül Bir Mimari
34th Signal Processing and Communications Applications Conference, SIU 2026, İstanbul, Türkiye, 7 - 10 Temmuz 2026, (Tam Metin Bildiri)
- Yayın Türü: Bildiri / Tam Metin Bildiri
- Doi Numarası: 10.1109/siu71813.2026.11636541
- Basıldığı Şehir: İstanbul
- Basıldığı Ülke: Türkiye
- Anahtar Kelimeler: hybrid retrieval, information retrieval, large language models, query expansion, retrieval-augmented generation
- Orta Doğu Teknik Üniversitesi Adresli: Hayır
Özet
Large language models may suffer from insufficient context use and unsupported generation in question answering tasks that require external knowledge. This study compares the main strategies affecting retrieval and generation performance in retrieval-augmented generation systems within a common experimental setting. In addition to a standard dense retrieval baseline, we evaluate multi-query, hypothetical document, hypothetical question, sparse-dense hybrid retrieval, and chunk compression, and we also propose an integrated method (FUSERAG) that combines these components. Experiments are conducted on a dataset containing 223 documents, 7933 chunks, and 1488 question-answer instances. Results show that the proposed method achieves the highest Mean Reciprocal Rank, nDCG at 5, and recall at 5 at the retrieval level, while the sparse-dense hybrid approach yields the best generation results.