List your company

Question Answering on HotpotQA (test) (Comprehensive Metrics)

0.822F1HGN
0.1700240.3392870.508550.677813Jan 27, 2022Aug 10, 2022Feb 22, 2023Sep 5, 2023Mar 19, 2024Sep 30, 2024Apr 14, 2025

Evaluation results

MethodLinks
HGNModel Category=Specialized Models2022.010.8220.692———————
POET-SQL_RoBERTaModel Category=Language Models, Model Size=Large2022.010.8160.687———————
C2F ReaderModel Category=Specialized Models2022.010.8120.68———————
SpanBERTModel Category=Language Models, Model Size=Large2022.010.8120.674———————
SAEModel Category=Specialized Models2022.010.8080.677———————
POET-SQL_BARTModel Category=Language Models, Model Size=Large2022.010.7970.665———————
ReasonBERTModel Category=Language Models, Model Size=not Large2022.010.7920.648———————
BERTModel Category=Language Models, Model Size=Large2022.010.7340.591———————
DFGNModel Category=Specialized Models2022.010.6930.557———————
IntegrationBackbone=Llama 3.1-70B2025.020.665—0.69220.667—————
IntegrationBackbone=Llama 3.1-8B2025.020.6476—0.67210.6509—————
GraphRAGBackbone=Llama 3.1-70B2025.020.646—0.6720.6489—————
RAGBackbone=Llama 3.1-70B2025.020.6388—0.66340.6399—————
GraphRAGBackbone=Llama 3.1-8B2025.020.6166—0.64140.6208—————
RAGBackbone=Llama 3.1-8B2025.020.6004—0.62320.6047—————
DioRLLM=Qwen2.5-7B, Retrieval=BM252025.040.25480.1630.26050.30522.5242.5531.263194.39512.273
RaDIOLLM=Qwen2.5-7B, Retrieval=BM252025.040.22360.1240.22610.30233.0243.9851.765200.39813.562
BaseLLM=Qwen2.5-7B, Retrieval=BM252025.040.19510.1110.19310.30032.9044.3862.094302.89419.146