List your company

Open-domain Question Answering on MusiQue out-of-domain

35.8F1UR2
8.65615.70322.7529.797Aug 8, 2025

Evaluation results

MethodLinks
UR2Backbone=Qwen-2.5-7B, Type=Our Implementations2025.0835.834.6
UR2Model=Qwen-2.5-7B, Type=Our Implementations2025.0835.834.6
Vanilla RLBackbone=Qwen-2.5-7B, Type=Our Implementations2025.0834.434.4
Vanilla RLModel=Qwen-2.5-7B, Type=Our Implementations2025.0834.434.4
UR2Backbone=LLaMA-3.1-8B, Type=Our Implementations2025.0834.334
UR2Model=LLaMA-3.1-8B, Type=Our Implementations2025.0834.334
R1-Searcher++Backbone=Qwen-2.5-7B, Type=RAG-RL2025.0833.832.8
R1-Searcher++Model=Qwen-2.5-7B, Type=RAG-RL2025.0833.832.8
R1-SearcherBackbone=Qwen-2.5-7B, Type=RAG-RL2025.0833.332.6
R1-SearcherModel=Qwen-2.5-7B, Type=RAG-RL2025.0833.332.6
Vanilla RLBackbone=LLaMA-3.1-8B, Type=Our Implementations2025.0832.731.8
Vanilla RLModel=LLaMA-3.1-8B, Type=Our Implementations2025.0832.731.8
Search-R1Backbone=Qwen-2.5-7B, Type=RAG-RL2025.0832.232
Search-R1Model=Qwen-2.5-7B, Type=RAG-RL2025.0832.232
Self-AskBackbone=GPT-4.1-mini, Type=Advanced RAG2025.0831.635
R1-SearcherBackbone=LLaMA-3.1-8B, Type=RAG-RL2025.0831.129.4
R1-SearcherModel=LLaMA-3.1-8B, Type=RAG-RL2025.0831.129.4
UR2Backbone=Qwen-2.5-3B, Type=Our Implementations2025.0830.531.6
UR2Model=Qwen-2.5-3B, Type=Our Implementations2025.0830.531.6
Vanilla RLBackbone=Qwen-2.5-3B, Type=Our Implementations2025.083029.6
Vanilla RLModel=Qwen-2.5-3B, Type=Our Implementations2025.083029.6
Search-o1Model=GPT-4o-mini, Type=Advanced RAG2025.0829.630.2
RATBackbone=GPT-4.1-mini, Type=Advanced RAG2025.082931.4
Search-o1Backbone=GPT-4.1-mini, Type=Advanced RAG2025.0828.633.4
CoTBackbone=GPT-4.1-mini, Type=Vanilla Methods2025.0828.335.4
Search-R1Backbone=Qwen-2.5-3B, Type=RAG-RL2025.0827.627.8
Search-R1Model=Qwen-2.5-3B, Type=RAG-RL2025.0827.627.8
Self-AskModel=GPT-4o-mini, Type=Advanced RAG2025.0826.127.8
CoTModel=GPT-4o-mini, Type=Vanilla Methods2025.0824.926.8
RATModel=GPT-4o-mini, Type=Advanced RAG2025.0824.324.8
Standard RAGBackbone=GPT-4.1-mini, Type=Vanilla Methods2025.0821.928.4
Search-o1Model=Qwen-2.5-7B, Type=Advanced RAG2025.0820.619.8
Standard RAGModel=GPT-4o-mini, Type=Vanilla Methods2025.0819.321.6
RATModel=LLaMA-3.1-8B, Type=Advanced RAG2025.081716
Zero-SearchBackbone=Qwen-2.5-3B, Type=RAG-RL2025.0816.917
Zero-SearchModel=Qwen-2.5-3B, Type=RAG-RL2025.0816.917
Self-AskModel=LLaMA-3.1-8B, Type=Advanced RAG2025.0816.816.4
Search-o1Model=LLaMA-3.1-8B, Type=Advanced RAG2025.0815.916.2
CoTBackbone=Qwen-2.5-7B, Type=Vanilla Methods2025.0814.812.2
CoTModel=Qwen-2.5-7B, Type=Vanilla Methods2025.0814.812.2
ZeroSearchBackbone=Qwen-2.5-7B, Type=RAG-RL2025.0814.713.8
ZeroSearchModel=Qwen-2.5-7B, Type=RAG-RL2025.0814.713.8
Self-AskModel=Qwen-2.5-3B, Type=Advanced RAG2025.0814.514.8
Standard RAGBackbone=Qwen-2.5-7B, Type=Vanilla Methods2025.0814.414.6
Standard RAGModel=Qwen-2.5-7B, Type=Vanilla Methods2025.0814.414.6
RATModel=Qwen-2.5-7B, Type=Advanced RAG2025.0814.412.4
Self-AskModel=Qwen-2.5-7B, Type=Advanced RAG2025.0813.619.6
Search-o1Model=Qwen-2.5-3B, Type=Advanced RAG2025.0812.510
CoTBackbone=Qwen-2.5-3B, Type=Vanilla Methods2025.0811.39.6
CoTModel=Qwen-2.5-3B, Type=Vanilla Methods2025.0811.39.6
RATModel=Qwen-2.5-3B, Type=Advanced RAG2025.08118.2
Standard RAGBackbone=LLaMA-3.1-8B, Type=Vanilla Methods2025.0810.110.2
Standard RAGModel=LLaMA-3.1-8B, Type=Vanilla Methods2025.0810.110.2
CoTBackbone=LLaMA-3.1-8B, Type=Vanilla Methods2025.089.810.8
CoTModel=LLaMA-3.1-8B, Type=Vanilla Methods2025.089.810.8
Standard RAGBackbone=Qwen-2.5-3B, Type=Vanilla Methods2025.089.77.4
Standard RAGModel=Qwen-2.5-3B, Type=Vanilla Methods2025.089.77.4