List your company

Question Answering on TrivialQA Noisy

55.09F1 ScoreOpenDecoder
25.689233.322140.95548.5879Jan 13, 2026

Evaluation results

MethodLinks
OpenDecoderBackbone=Qwen-2.5-3B-Instruct2026.0155.0953.33
RbFTBackbone=Qwen-2.5-3B-Instruct2026.0152.6251.7
Vanilla SFTBackbone=Qwen-2.5-3B-Instruct2026.0148.5448.07
AstuteRAGBackbone=Qwen-2.5-3B-Instruct2026.0146.8148.7
InstructRAGBackbone=Qwen-2.5-3B-Instruct2026.0144.1348.2
RobustRAGBackbone=Qwen-2.5-3B-Instruct2026.0142.3644.53
Vanilla RAGBackbone=Qwen-2.5-3B-Instruct2026.0126.8249.93