List your company

Question Answering on HotpotQA (EM, F1, Precision, Recall)

89.5RecallAGDLRPc
22.9440.2257.574.78Apr 14, 2025May 12, 2025Jun 9, 2025Jul 7, 2025Aug 4, 2025Sep 1, 2025Sep 30, 2025

Evaluation results

MethodLinks
AGDLRPcModel=Qwen 2.5 (7B), Setting=Open-book2025.0989.5———
AGDLRPhModel=Llama 3.1 (8B), Setting=Open-book2025.0987.9———
AGDLRPcModel=Llama 3.1 (8B), Setting=Open-book2025.0987.9———
AGDLRPhModel=Qwen 2.5 (7B), Setting=Open-book2025.0986.4———
AGDI×GhModel=Qwen 2.5 (7B), Setting=Open-book2025.0985.5———
AGDI×GcModel=Qwen 2.5 (7B), Setting=Open-book2025.0985.1———
NucleusModel=Qwen 2.5 (7B), Setting=Open-book2025.0985———
CADModel=Qwen 2.5 (7B), Setting=Open-book2025.0985———
GreedyModel=Qwen 2.5 (7B), Setting=Open-book2025.0984.5———
AGDI×GcModel=Llama 3.1 (8B), Setting=Open-book2025.0983.9———
CADModel=Llama 3.1 (8B), Setting=Open-book2025.0983.4———
AGDI×GhModel=Llama 3.1 (8B), Setting=Open-book2025.0981.6———
GreedyModel=Llama 3.1 (8B), Setting=Open-book2025.0981.3———
NucleusModel=Llama 3.1 (8B), Setting=Open-book2025.0980.7———
AGDLRPcModel=Gemma 3 (4B), Setting=Open-book2025.0970.9———
AGDLRPhModel=Gemma 3 (4B), Setting=Open-book2025.0970.6———
AGDI×GhModel=Gemma 3 (4B), Setting=Open-book2025.0970.4———
GreedyModel=Gemma 3 (4B), Setting=Open-book2025.0970.1———
AGDI×GcModel=Gemma 3 (4B), Setting=Open-book2025.0970.1———
NucleusModel=Gemma 3 (4B), Setting=Open-book2025.0969.8———
CADModel=Gemma 3 (4B), Setting=Open-book2025.0964.1———
AGDLRPhModel=Llama 3.1 (8B), Setting=Closed-book2025.0939.6———
DioRRetrieval Strategy=BM25, Backbone=LLaMA2-7B-CHAT2025.0438.127.437.939.9
AGDI×GhModel=Llama 3.1 (8B), Setting=Closed-book2025.0937.5———
GreedyModel=Llama 3.1 (8B), Setting=Closed-book2025.0934.6———
DoLAModel=Llama 3.1 (8B), Setting=Closed-book2025.0934.3———
AGDLRPhModel=Qwen 2.5 (7B), Setting=Closed-book2025.0934.3———
GreedyModel=Qwen 2.5 (7B), Setting=Closed-book2025.0933.8———
AGDI×GhModel=Qwen 2.5 (7B), Setting=Closed-book2025.0933.6———
NucleusModel=Qwen 2.5 (7B), Setting=Closed-book2025.0932.5———
DoLAModel=Qwen 2.5 (7B), Setting=Closed-book2025.0932.4———
NucleusModel=Llama 3.1 (8B), Setting=Closed-book2025.0931.9———
DraginRetrieval Strategy=BM25, Backbone=LLaMA2-7B-CHAT2025.0431.621.931.433.1
DioRRetrieval Strategy=SGPT, Backbone=LLaMA2-7B-CHAT2025.0431.221.230.733.3
DraginRetrieval Strategy=SGPT, Backbone=LLaMA2-7B-CHAT2025.0430.520.230.131.9
DioRRetrieval Strategy=SBERT, Backbone=LLaMA2-7B-CHAT2025.0430.320.530.332.4
AGDI×GhModel=Gemma 3 (4B), Setting=Closed-book2025.0928———
AGDLRPhModel=Gemma 3 (4B), Setting=Closed-book2025.0928———
GreedyModel=Gemma 3 (4B), Setting=Closed-book2025.0927.7———
NucleusModel=Gemma 3 (4B), Setting=Closed-book2025.0927.7———
DoLAModel=Gemma 3 (4B), Setting=Closed-book2025.0927.3———
DraginRetrieval Strategy=SBERT, Backbone=LLaMA2-7B-CHAT2025.0425.516.524.425.6