List your company

Knowledge-intensive Question Answering on OpenScience

53.8Pass@1P-POTS+Mirror
45.001647.285849.5751.8542Nov 22, 2025

Evaluation results

MethodLinks
P-POTS+MirrorBackbone=LLaDA-8B-Instruct, Seed=731, Decoding=Greedy, Mode=Supervised fine-tuning2025.1153.8
P-POTS+MirrorBackbone=LLaDA-8B-Instruct, Seed=20231, Decoding=Greedy, Mode=Supervised fine-tuning2025.1153
P-POTS+MirrorBackbone=LLaDA-8B-Instruct, Seed=Avg, Decoding=Greedy, Mode=Supervised fine-tuning2025.1152.53
Qwen3-8B-BaseSeed=Avg2025.1151.62
P-POTS+MirrorBackbone=LLaDA-8B-Instruct, Seed=42, Decoding=Greedy, Mode=Supervised fine-tuning2025.1150.8
ClippedBackbone=LLaDA-8B-Instruct, Seed=Avg2025.1149.33
P-POTSBackbone=LLaDA-8B-Instruct, Seed=731, Decoding=Greedy2025.1147.6
P-POTSBackbone=LLaDA-8B-Instruct, Seed=20231, Decoding=Greedy2025.1147.47
EMABackbone=LLaDA-8B-Instruct, Seed=422025.1147.08
P-POTSBackbone=LLaDA-8B-Instruct, Seed=Avg, Decoding=Greedy2025.1146.8
Llama3.1-8B-InstructSeed=Avg2025.1146.59
Qwen2.5-7B-InstructSeed=Avg, Type=Auto-Regressive LLM2025.1146.42
MIRRORBackbone=LLaDA-8B-Instruct, Seed=Avg2025.1146.38
StandardBackbone=LLaDA-8B-Instruct, Seed=Avg2025.1145.52
ISADBackbone=LLaDA-8B-Instruct, Seed=Avg2025.1145.4
P-POTSBackbone=LLaDA-8B-Instruct, Seed=42, Decoding=Greedy2025.1145.34