List your company

Question Answering on XOR-TyDi QA

0.383fEMLCRL
0.088680.165090.24150.31791Jan 21, 2026

Evaluation results

MethodLinks
LCRLBase Model=Qwen3-8B2026.010.3830.4890.993
D-RAGBase Model=Qwen3-8B2026.010.3350.4230.935
LCRLBase Model=Qwen3-4B2026.010.3240.4570.994
LCRLBase Model=Qwen2.5-3B-Instruct2026.010.3170.4390.992
D-RAGBase Model=Qwen2.5-3B-Instruct2026.010.3150.3890.871
D-RAGBase Model=Qwen3-4B2026.010.3110.3870.903
SFTBase Model=Qwen3-8B2026.010.30.3890.94
SFTBase Model=Qwen2.5-3B-Instruct2026.010.2830.3550.877
SFTBase Model=Qwen3-4B2026.010.2820.3560.916
mSearch-R1Base Model=Qwen3-8B2026.010.2720.3850.942
Search-o1Base Model=Qwen3-8B2026.010.2520.3430.746
IRCoTBase Model=Qwen3-8B2026.010.240.330.719
mSearch-R1Base Model=Qwen3-4B2026.010.2340.3660.946
RAGBase Model=Qwen3-8B2026.010.2270.3180.749
mSearch-R1Base Model=Qwen2.5-3B-Instruct2026.010.2120.3580.941
Search-o1Base Model=Qwen2.5-3B-Instruct2026.010.2110.3070.679
IRCoTBase Model=Qwen3-4B2026.010.2070.2810.696
RAGBase Model=Qwen3-4B2026.010.2070.2810.717
RAGBase Model=Qwen2.5-3B-Instruct2026.010.20.2910.652
Search-o1Base Model=Qwen3-4B2026.010.1960.2670.731
IRCoTBase Model=Qwen2.5-3B-Instruct2026.010.1850.2790.694
Search-R1Base Model=Qwen2.5-3B-Instruct2026.010.1840.320.863
Search-R1Base Model=Qwen3-4B2026.010.1780.2980.872
Search-R1Base Model=Qwen3-8B2026.010.1680.2810.889
Direct InferenceBase Model=Qwen3-8B2026.010.1230.2270.675
Direct InferenceBase Model=Qwen2.5-3B-Instruct2026.010.1010.190.706
Direct InferenceBase Model=Qwen3-4B2026.010.10.2030.661