List your company
ResearchFormerly WizWand

Question Answering on MOAMOB

27.14ANLSM3DOCDEP
24.446425.145725.84526.5443Apr 14, 2026Apr 15, 2026Apr 16, 2026Apr 17, 2026
Updated 5mo ago

Evaluation results

MethodLinks
M3DOCDEPtop-k={1, 2, 3, 4}, Readers=LLaVA-OneVision-1.5, InternVL-3.5, and Qwen2.5-VL, RAG protocol=shared corpus-level RAG protocol2026.0427.1410.2214.68
MultiDocFusiontop-k={1, 4}, Models=Llama-3.2-3B, Mistral-8B, Qwen-2.5-7B (averaged)2026.0425.969.1612.57
MultiDocFusiontop-k={1, 2, 3, 4}, Readers=LLaVA-OneVision-1.5, InternVL-3.5, and Qwen2.5-VL, RAG protocol=shared corpus-level RAG protocol2026.0425.969.1612.57
LumberChunkertop-k={1, 4}, Models=Llama-3.2-3B, Mistral-8B, Qwen-2.5-7B (averaged)2026.0425.368.4811.67
LumberChunkertop-k={1, 2, 3, 4}, Readers=LLaVA-OneVision-1.5, InternVL-3.5, and Qwen2.5-VL, RAG protocol=shared corpus-level RAG protocol2026.0425.368.4811.67
Perplexity chunkingtop-k={1, 4}, Models=Llama-3.2-3B, Mistral-8B, Qwen-2.5-7B (averaged)2026.0425.328.9411.9
Perplexity chunkingtop-k={1, 2, 3, 4}, Readers=LLaVA-OneVision-1.5, InternVL-3.5, and Qwen2.5-VL, RAG protocol=shared corpus-level RAG protocol2026.0425.328.9411.9
Structure-based chunkingtop-k={1, 4}, Models=Llama-3.2-3B, Mistral-8B, Qwen-2.5-7B (averaged)2026.0425.019.7911.14
Structure-based chunkingtop-k={1, 2, 3, 4}, Readers=LLaVA-OneVision-1.5, InternVL-3.5, and Qwen2.5-VL, RAG protocol=shared corpus-level RAG protocol2026.0425.019.7911.14
Length chunkingtop-k={1, 4}, Models=Llama-3.2-3B, Mistral-8B, Qwen-2.5-7B (averaged)2026.0424.978.2311.15
Length chunkingtop-k={1, 2, 3, 4}, Readers=LLaVA-OneVision-1.5, InternVL-3.5, and Qwen2.5-VL, RAG protocol=shared corpus-level RAG protocol2026.0424.978.2311.15
Semantic chunkingtop-k={1, 4}, Models=Llama-3.2-3B, Mistral-8B, Qwen-2.5-7B (averaged)2026.0424.558.4610.43
Semantic chunkingtop-k={1, 2, 3, 4}, Readers=LLaVA-OneVision-1.5, InternVL-3.5, and Qwen2.5-VL, RAG protocol=shared corpus-level RAG protocol2026.0424.558.4610.43