List your company

Document Retrieval on DUDE

25.17Recall@1only Segmentation
12.606815.868419.1322.3916Apr 9, 2026

Evaluation results

MethodLinks
only SegmentationEmbedding Model=gte-base-en-v1.52026.0425.1730.5433.22————
only SegmentationEmbedding Model=e5-large-v22026.0424.8330.233.89————
REVISE_metaEmbedding Model=gte-base-en-v1.52026.0423.1531.2135.91————
REVISE_metaEmbedding Model=bge-large-en-v1.52026.0422.8231.2135.23————
only ColumnEmbedding Model=gte-base-en-v1.52026.0422.8230.234.23————
REVISE_metaEmbedding Model=e5-large-v22026.0422.4829.8732.55————
only ColumnEmbedding Model=bge-large-en-v1.52026.0422.1533.2236.91————
only SegmentationEmbedding Model=bge-large-en-v1.52026.0422.1530.8736.58————
only DeletionEmbedding Model=e5-large-v22026.0422.1529.1932.89————
only SubstitutionEmbedding Model=gte-base-en-v1.52026.0422.1530.233.56————
only TranspositionEmbedding Model=gte-base-en-v1.52026.0421.8128.8633.56————
only ColumnEmbedding Model=e5-large-v22026.0421.4832.2137.92————
only SubstitutionEmbedding Model=e5-large-v22026.0420.4728.1932.21————
BaselineEmbedding Model=gte-base-en-v1.52026.0420.4728.8631.88————
only DeletionEmbedding Model=gte-base-en-v1.52026.0420.4729.8734.23————
BaselineEmbedding Model=bge-large-en-v1.52026.0420.1330.8734.9————
only SubstitutionEmbedding Model=bge-large-en-v1.52026.0420.1329.8734.56————
BaselineEmbedding Model=e5-large-v22026.0420.1327.1831.88————
only InsertionEmbedding Model=e5-large-v22026.0419.828.1930.54————
only TranspositionEmbedding Model=e5-large-v22026.0419.827.1831.88————
REVISE_metaEmbedding Model=jina-embeddings-v2-base2026.0419.828.1932.21————
only DeletionEmbedding Model=bge-large-en-v1.52026.0419.4629.5332.89————
only InsertionEmbedding Model=bge-large-en-v1.52026.0419.1329.5334.56————
only SubstitutionEmbedding Model=jina-embeddings-v2-base2026.0419.1328.5230.87————
only TranspositionEmbedding Model=bge-large-en-v1.52026.0418.4629.8734.23————
only InsertionEmbedding Model=gte-base-en-v1.52026.0418.4629.8734.23————
only ColumnEmbedding Model=jina-embeddings-v2-base2026.0418.1227.8531.54————
only DeletionEmbedding Model=jina-embeddings-v2-base2026.0417.7925.528.86————
only SegmentationEmbedding Model=jina-embeddings-v2-base2026.0417.7923.4928.86————
only TranspositionEmbedding Model=jina-embeddings-v2-base2026.0417.7923.8328.86————
BaselineEmbedding Model=jina-embeddings-v2-base2026.0413.4218.4625.84————
only InsertionEmbedding Model=jina-embeddings-v2-base2026.0413.0917.1126.17————
BaselineEmbedding Model=Aggregate (All Models)2026.04———25.34———
Length chunkingtop-k=1 ~ 42026.04————26.2816.8621.66
Length chunkingRetrievers=Averaged over BGE, E5, BM25, MM-Embed, Top-k=macro-averaged for {1, 2, 3, 4}, RAG Protocol=Shared corpus-level2026.04————26.2816.8621.66
LumberChunkertop-k=1 ~ 42026.04————23.9515.3319.86
LumberChunkerRetrievers=Averaged over BGE, E5, BM25, MM-Embed, Top-k=macro-averaged for {1, 2, 3, 4}, RAG Protocol=Shared corpus-level2026.04————23.9515.3319.86
M3DOCDEPRetrievers=Averaged over BGE, E5, BM25, MM-Embed, Top-k=macro-averaged for {1, 2, 3, 4}, RAG Protocol=Shared corpus-level2026.04————35.1224.9127.81
MultiDocFusiontop-k=1 ~ 42026.04————29.2720.0125.05
MultiDocFusionRetrievers=Averaged over BGE, E5, BM25, MM-Embed, Top-k=macro-averaged for {1, 2, 3, 4}, RAG Protocol=Shared corpus-level2026.04————29.2720.0125.05
only ColumnEmbedding Model=Aggregate (All Models)2026.04———30.76———
only DeletionEmbedding Model=Aggregate (All Models)2026.04———27.29———
only InsertionEmbedding Model=Aggregate (All Models)2026.04———27.74———
only SegmentationEmbedding Model=Aggregate (All Models)2026.04———29.87———
only SubstitutionEmbedding Model=Aggregate (All Models)2026.04———28.19———
only TranspositionEmbedding Model=Aggregate (All Models)2026.04———27.52———
Perplexity chunkingtop-k=1 ~ 42026.04————24.2815.5920.2
Perplexity chunkingRetrievers=Averaged over BGE, E5, BM25, MM-Embed, Top-k=macro-averaged for {1, 2, 3, 4}, RAG Protocol=Shared corpus-level2026.04————24.2815.5920.2
REVISE_metaEmbedding Model=Aggregate (All Models)2026.04———29.75———
Semantic chunkingtop-k=1 ~ 42026.04————9.565.497.75
Semantic chunkingRetrievers=Averaged over BGE, E5, BM25, MM-Embed, Top-k=macro-averaged for {1, 2, 3, 4}, RAG Protocol=Shared corpus-level2026.04————9.565.497.75
Structure-based chunkingtop-k=1 ~ 42026.04————22.1914.518.62
Structure-based chunkingRetrievers=Averaged over BGE, E5, BM25, MM-Embed, Top-k=macro-averaged for {1, 2, 3, 4}, RAG Protocol=Shared corpus-level2026.04————22.1914.518.62