List your company

Retrieval-Augmented Generation on Historical Newspaper Archives 384 queries k=10

87.63Context RelevanceOurs - LLM(Semantic + BM25s) + reranker
68.878873.746978.61583.4831Jul 3, 2026

Evaluation results

MethodLinks
Ours - LLM(Semantic + BM25s) + rerankerk=10, OCR Sanitization=Gemini 1.5 Flash, Retrieval Strategy=Hybrid, Reranker=Enabled, Embedding Model=text-embedding-2-preview, Generator LLM=GPT-4o-mini2026.0787.6365.9287.05
Semantic + BM25s + rerankerk=10, OCR Sanitization=None, Retrieval Strategy=Hybrid, Reranker=Enabled, Embedding Model=text-embedding-2-preview, Generator LLM=GPT-4o-mini2026.0785.0363.684.94
LLM(Semantic + BM25s)k=10, OCR Sanitization=Gemini 1.5 Flash, Retrieval Strategy=Hybrid, Reranker=Disabled, Embedding Model=text-embedding-2-preview, Generator LLM=GPT-4o-mini2026.0777.9962.6269.71
Semantic + BM25sk=10, OCR Sanitization=None, Retrieval Strategy=Hybrid, Reranker=Disabled, Embedding Model=text-embedding-2-preview, Generator LLM=GPT-4o-mini2026.0775.3961.4374.35
LLM(Semantic)k=10, OCR Sanitization=Gemini 1.5 Flash, Retrieval Strategy=Dense, Reranker=Disabled, Embedding Model=text-embedding-2-preview, Generator LLM=GPT-4o-mini2026.0773.1854.7462.93
Semantick=10, OCR Sanitization=None, Retrieval Strategy=Dense, Reranker=Disabled, Embedding Model=text-embedding-2-preview, Generator LLM=GPT-4o-mini2026.0771.2954.7363.69
BM25sk=10, OCR Sanitization=None, Retrieval Strategy=Lexical, Reranker=Disabled, Embedding Model=N/A, Generator LLM=GPT-4o-mini2026.0770.5156.1565.99
LLM(BM25s)k=10, OCR Sanitization=Gemini 1.5 Flash, Retrieval Strategy=Lexical, Reranker=Disabled, Embedding Model=N/A, Generator LLM=GPT-4o-mini2026.0769.657.4565.51