List your company

General Question Answering on PopQA (EM, LLM)

47.9EMDAC
14.122.87531.6540.425Jun 9, 2026

Evaluation results

MethodLinks
DACBackbone=Qwen3-8B, FT=LoRA2026.0647.952.9
Search-R1 (GRPO/O)Backbone=Qwen3-8B, FT=Full2026.0646.951.6
Search-R1 (PPO/OF)Backbone=Qwen3-8B, FT=Full2026.0645.850.4
Search-R1 (GRPO/OF)Backbone=Qwen3-8B, FT=Full2026.0645.350.4
Search-R1 (PPO/O)Backbone=Qwen3-8B, FT=Full2026.0643.448
Search-R1 (GRPO/O)Backbone=Qwen2.5-7B-Instruct, FT=Full2026.0642.647.5
DACBackbone=Qwen2.5-7B-Instruct, FT=LoRA2026.0641.147.6
Search-R1 (GRPO/OF)Backbone=Qwen2.5-7B-Instruct, FT=Full2026.0639.946.5
Search-R1 (PPO/O)Backbone=Qwen2.5-7B-Instruct, FT=Full2026.0639.545.9
Naive RAGBackbone=Qwen2.5-7B-Instruct, FT=-2026.0638.946.8
Naive RAGBackbone=Qwen3-8B, FT=-2026.0638.745.5
Search-R1 (PPO/OF)Backbone=Qwen2.5-7B-Instruct, FT=Full2026.0637.944.6
IRCoTBackbone=Qwen3-8B, FT=-2026.0636.350
Search-o1Backbone=Qwen3-8B, FT=-2026.0635.745.3
Search-o1Backbone=Qwen2.5-7B-Instruct, FT=-2026.0633.641.1
IRCoTBackbone=Qwen2.5-7B-Instruct, FT=-2026.0620.745.6
DirectBackbone=Qwen2.5-7B-Instruct, FT=-2026.0616.519.2
CoTBackbone=Qwen2.5-7B-Instruct, FT=-2026.061619
CoTBackbone=Qwen3-8B, FT=-2026.0615.919.9
DirectBackbone=Qwen3-8B, FT=-2026.0615.420.5