List your company

Question Answering on HotpotQA Noisy

28.76F1 ScoreOpenDecoder
10.341615.123319.90524.6867Jan 13, 2026

Evaluation results

MethodLinks
OpenDecoderBackbone=Qwen-2.5-3B-Instruct2026.0128.7622.77
RbFTBackbone=Qwen-2.5-3B-Instruct2026.0125.2819
AstuteRAGBackbone=Qwen-2.5-3B-Instruct2026.0123.6317
Vanilla SFTBackbone=Qwen-2.5-3B-Instruct2026.0123.5520.8
InstructRAGBackbone=Qwen-2.5-3B-Instruct2026.0118.1611.6
RobustRAGBackbone=Qwen-2.5-3B-Instruct2026.0112.0414.13
Vanilla RAGBackbone=Qwen-2.5-3B-Instruct2026.0111.0519