List your company

Multi-hop Question Answering on IIRC

29EMCheckRLM
8.82414.06219.324.538May 31, 2025Aug 5, 2025Oct 10, 2025Dec 15, 2025Feb 19, 2026Apr 26, 2026Jul 2, 2026

Evaluation results

MethodLinks
CheckRLMBackbone=QwQ-32B2026.072933.1
Q-DREAMBackbone=ChatGPT2025.0528.231.9
CheckRLMBackbone=Qwen3-32B2026.0727.831.6
CheckRLMBackbone=Qwen3-8B2026.0725.429.7
Search-o1Backbone=QwQ-32B2026.072529.2
Q-DREAMBackbone=Llama2-7B2025.0523.827.2
Vanilla RAGBackbone=QwQ-32B2026.072225
ChatQA2Backbone=Llama3-8B2025.0521.425.7
Direct ReasoningBackbone=QwQ-32B2026.0721.424.8
Self-RAGBackbone=QwQ-32B2026.0721.325.1
IRCoTBackbone=ChatGPT2025.052131
SUREBackbone=ChatGPT2025.0520.625.5
Direct ReasoningBackbone=Qwen3-32B2026.0720.223
Vanilla RAGBackbone=Qwen3-32B2026.0719.822.5
Direct ReasoningBackbone=Qwen3-8B2026.0718.221
RATBackbone=QwQ-32B2026.071721.7
Vanilla RAGBackbone=Qwen3-8B2026.0716.819.8
ReActBackbone=QwQ-32B2026.0716.221.9
InstructRAGBackbone=Llama3-8B2025.0514.218.1
ChatGPTBackbone=GPT-3.5-turbo2025.0511.413.8
FLAREBackbone=QwQ-32B2026.079.612.3