List your company

Multi-Hop Question Answering on MuSiQue (EM & F1)

33.5Exact Match (EM)QAFD-RAG
-1.2367.78216.825.818Oct 18, 2025Nov 17, 2025Dec 18, 2025Jan 18, 2026Feb 18, 2026Mar 21, 2026Apr 21, 2026

Evaluation results

MethodLinks
QAFD-RAGLLM=GPT-4o2026.0433.547.99
DTKG (Full)Backbone=Llama 3.1:8B2025.1033.545.2
CoRAGBackbone=Llama 3.1:8B2025.1030.942.4
HippoRAGLLM=GPT-4o2026.0427.5538.33
TOGBackbone=Llama 3.1:8B2025.1026.838.4
KGRBackbone=Llama 3.1:8B2025.1025.436.2
CRITICBackbone=Llama 3.1:8B2025.1023.533.8
Self-Correcting RAGCategory=Self-Correcting RAG2026.0422.731.9
COTBackbone=Llama 3.1:8B2025.1022.132.5
RECOMPCategory=Advanced Selection & Reranking2026.0421.530.2
RRRCategory=Standard RAG Baselines2026.0420.529.5
DRAGCategory=Iterative & Agentic RAG2026.0420.428.1
Self-RAGCategory=Iterative & Agentic RAG2026.0420.229.1
RAG + MMRCategory=Advanced Selection & Reranking2026.0419.828.4
FilcoCategory=Advanced Selection & Reranking2026.0419.528.1
IRCoTCategory=Iterative & Agentic RAG2026.0418.527.8
HyDECategory=Standard RAG Baselines2026.0418.227.5
CRAGCategory=Iterative & Agentic RAG2026.0418.227.8
LongLLMLinguaCategory=Advanced Selection & Reranking2026.0417.826.5
GraphRAGLLM=GPT-4o2026.0417.639.4
NaiveCategory=Standard RAG Baselines2026.0414.625.8
RAPTORLLM=GPT-4o2026.0410.528.1
LightRAGLLM=GPT-4o2026.040.11.4