List your company

Multi-hop Question Answering on MuSiQue (EM, F1, Judge)

46.1Exact Match (EM)Agentic Hybrid
3.064814.237425.4136.5826May 26, 2026Jun 2, 2026Jun 9, 2026Jun 16, 2026Jun 23, 2026Jun 30, 2026Jul 7, 2026

Evaluation results

MethodLinks
Agentic HybridCorpus=Medium-scale2026.0546.157.366.2
LOGICALRAGCorpus=Medium-scale2026.05415259.5
HippoRAG2Corpus=Medium-scale2026.0536.648.951.5
MA-RAGCorpus=Medium-scale2026.0533.548.554.5
Direct AnswerCorpus=Medium-scale2026.052032.434
CEHop=2-hop, Retrieval Setting=Multi-step2026.0713.34——
SetCEHop=2-hop, Retrieval Setting=Single-step2026.0711.88——
BiHop=2-hop, Retrieval Setting=Multi-step2026.0711.72——
ParaSet+SetCEHop=2-hop, Retrieval Setting=Single-step2026.0710.35——
SetCEHop=3-hop, Retrieval Setting=Single-step2026.079.53——
ParaSet+SetCE (∪ CE)Hop=2-hop, Retrieval Setting=Single-step2026.079.32——
ParaSet+SetCE (∪ CE)Hop=3-hop, Retrieval Setting=Single-step2026.079.32——
ParaSet+SetCE (∪ CE)Hop=Macro Avg, Retrieval Setting=Single-step2026.079.3——
ParaSet+SetCE (∪ CE)Hop=4-hop, Retrieval Setting=Single-step2026.079.27——
SetCEHop=Macro Avg, Retrieval Setting=Single-step2026.078.98——
CEHop=Macro Avg, Retrieval Setting=Multi-step2026.078.71——
BiHop=Macro Avg, Retrieval Setting=Multi-step2026.078.47——
BiHop=3-hop, Retrieval Setting=Multi-step2026.078.19——
CEHop=3-hop, Retrieval Setting=Multi-step2026.078.05——
ParaSet+SetCEHop=Macro Avg, Retrieval Setting=Single-step2026.077.3——
ParaSet+SetCEHop=3-hop, Retrieval Setting=Single-step2026.075.77——
ParaSet+SetCEHop=4-hop, Retrieval Setting=Single-step2026.075.77——
BiHop=4-hop, Retrieval Setting=Multi-step2026.075.51——
SetCEHop=4-hop, Retrieval Setting=Single-step2026.075.51——
CEHop=4-hop, Retrieval Setting=Multi-step2026.074.72——