Question Answering On Nq Beir

nDCG@10

評価結果

このベンチマークにおける各モデルのパフォーマンス結果

		Paper Title
Blended RAG	0.67	Blended RAG: Improving RAG (Retriever-Augmented Generation) Accuracy with Semantic Search and Hybrid Query-Based Retrievers
monoT5-3B	0.633	No Parameter Left Behind: How Distillation and Model Size Affect Zero-Shot Retrieval
BM25+CE	0.533	BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Models
SGPT-BE-5.8B	0.524	SGPT: GPT Sentence Embeddings for Semantic Search
ColBERT	0.524	BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Models
SGPT-CE-6.1B	0.401	SGPT: GPT Sentence Embeddings for Semantic Search

0 of 6 row(s) selected.