List your company

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

72F1 ScoreDIRECT QUERY
-0.818.13755.9Dec 30, 2023May 22, 2024Oct 13, 2024Mar 6, 2025Jul 28, 2025Dec 19, 2025May 12, 2026

Evaluation results

MethodLinks
DIRECT QUERYPRIVATE=NO, Backbone=GPT-4O2023.12727256
CONFUSIONPROMPTPRIVATE=YES, Backbone=GPT-4O2023.12686854
DIRECT QUERYPRIVATE=NO, Backbone=GPT-4-TURBO2023.12666650
CONFUSIONPROMPTPRIVATE=YES, Backbone=GPT-4-TURBO2023.12636350
CONFUSIONPROMPTPRIVATE=YES, Backbone=GPT-3.5-TURBO2023.12616145
DIRECT QUERYPRIVATE=NO, Backbone=GPT-3.5-TURBO2023.12606144
SAGEvariant=+2 round, Avg. Rank=2.52026.0553.1—34.2
SAGEvariant=+ IRCoT, Avg. Rank=3.32026.0552.6—35.2
SAGEvariant=+1 round, Avg. Rank=4.22026.0552.3—32.2
GFM-RAG + IRCoTAvg. Rank=3.72026.0549.2—36.6
LLAMA2-7BPRIVATE=YES2023.12484832
SAGEAvg. Rank=7.52026.0547.3—28
VICUNA-13BPRIVATE=YES2023.12424223
PropRAGAvg. Rank=3.82026.0541.3—38.9
HippoRAG 2Avg. Rank=4.72026.0540.5—33.9
GFM-RAGAvg. Rank=7.82026.0540.4—30.2
SubgraphRAGAvg. Rank=7.52026.0539.2—33
HippoRAG + IRCoTAvg. Rank=11.32026.0533.3—21.9
ColBERTv2 + IRCoTAvg. Rank=14.42026.0530.5—19.1
HippoRAGAvg. Rank=13.82026.0529.8—19.2
GraphRAGAvg. Rank=18.02026.0529.5—13.4
RAPTORAvg. Rank=15.82026.0528.9—17.6
FLAREAvg. Rank=12.72026.0528.4—16.2
LightRAGAvg. Rank=16.72026.0527.5—18.1
ColBERTv2Avg. Rank=17.32026.0526.4—15.5
G-RetrieverAvg. Rank=18.22026.0525.9—18
Adaptive-RAGAvg. Rank=14.32026.0525.6—13.8
GTRAvg. Rank=19.72026.0525.2—15.1
BM25Avg. Rank=15.52026.0523.6—19.5
ContrieverAvg. Rank=20.52026.0521.6—16.3
PARAPHRASERPRIVATE=YES, Backbone=GPT-3.5-TURBO2023.12883
PARAPHRASERPRIVATE=YES, Backbone=GPT-4O2023.12774
PARAPHRASERPRIVATE=YES, Backbone=GPT-4-TURBO2023.12663
TEXT2TEXTPRIVATE=YES, Backbone=GPT-4-TURBO2023.12331
TEXT2TEXTPRIVATE=YES, Backbone=GPT-3.5-TURBO2023.12221
TEXT2TEXTPRIVATE=YES, Backbone=GPT-4O2023.12221