List your company

Question Answering on MuSiQue (EM, F1)

39.7EMIRCoT
0.80410.9022131.098Aug 4, 2025Sep 29, 2025Nov 24, 2025Jan 19, 2026Mar 16, 2026May 11, 2026Jul 7, 2026

Evaluation results

MethodLinks
IRCoTInference LLM=Gemini-2.5-flash2025.0839.749.8
T^2RAGInference LLM=Gemini-2.5-flash2025.0839.149.1
Ψ-RAG ⍋Type=Tree-RAG, Reranker=Qwen3-Reranker-8B (Q3R), Abstract Type=summative2026.0538.748.9
Ψ-RAG øType=Tree-RAG, Reranker=Qwen3-Reranker-8B (Q3R), Abstract Type=keyword2026.0537.947.83
HippoRAG 2Type=Graph-RAG2026.0537.548
T^2RAGInference LLM=GPT-4o-mini2025.0834.345.6
HippoRAG2Inference LLM=GPT-4o-mini2025.0834.148.1
IRCoTInference LLM=GPT-4o-mini2025.0834.147.6
HippoRAG 2 + Q3RType=Graph-RAG, Reranker=Qwen3-Reranker-8B (Q3R)2026.0532.943.27
RAPTORInference LLM=Gemini-2.5-flash2025.0831.839.7
StandardInference LLM=GPT-4o-mini2025.0831.244.3
VECTORRAGLLM=GPT-OSS-120B2026.0530.443.6
DPR + IRCoT + Q3RType=Traditional RAG, Reranker=Qwen3-Reranker-8B (Q3R), Iterative Retrieval Protocol=IRCoT2026.0529.737.36
HippoRAG2Inference LLM=Gemini-2.5-flash2025.0829.138.3
RAPTORInference LLM=GPT-4o-mini2025.0828.640.8
BM25 + DPR + Q3RType=Traditional RAG, Reranker=Qwen3-Reranker-8B (Q3R)2026.0528.334.81
StandardInference LLM=Gemini-2.5-flash2025.0828.136.2
GraphRAGType=Graph-RAG2026.0525.830.7
M2RModel Family=Mistral-7B-Instruct2026.0425.5—
WIKONTICLLM=Qwen3-30B-A3B2026.052537.4
OAKLLM=Qwen3-30B-A3B2026.0524.436.5
ReSearchModel Family=Mistral-7B-Instruct2026.0423.7—
OAK+MENDLLM=Qwen3-30B-A3B2026.0523.335.2
OAKLLM=GPT-OSS-120B2026.0522.631.1
M2RModel Family=Llama-3.1-8B-Instruct2026.0422.1—
HIPPORAGV2LLM=Qwen3-30B-A3B2026.052233.9
IN-CONTEXTLLM=Qwen3-30B-A3B2026.052234
KGGENLLM=GPT-OSS-120B2026.0521.928.6
OAK+MENDLLM=GPT-OSS-120B2026.0521.529.9
SUREModel Family=Mistral-7B-Instruct2026.0421.2—
ReSearchModel Family=Llama-3.1-8B-Instruct2026.0420.9—
WIKONTICLLM=GPT-OSS-120B2026.0519.928
HIPPORAGV2LLM=GPT-OSS-120B2026.0519.436.2
KGGENLLM=Qwen3-30B-A3B2026.0519.229.2
DPRType=Traditional RAG2026.0518.724.03
SUREModel Family=Llama-3.1-8B-Instruct2026.0418.7—
COFTModel Family=Mistral-7B-Instruct2026.0418.5—
IN-CONTEXTLLM=GPT-OSS-120B2026.0517.523.7
RAPTOR + Q3RType=Tree-RAG, Reranker=Qwen3-Reranker-8B (Q3R)2026.0516.621.1
NORInference LLM=Gemini-2.5-flash2025.0816.326.5
COFTModel Family=Llama-3.1-8B-Instruct2026.0415.8—
BM25Inference LLM=GPT-4o-mini2025.0815.321.1
VECTORRAGLLM=Qwen3-30B-A3B2026.051423.2
BM25Type=Traditional RAG2026.051317.96
ZEROSHOTLLM=GPT-OSS-120B2026.0512.924.1
Naive RAGModel Family=Mistral-7B-Instruct2026.0411.3—
NORInference LLM=GPT-4o-mini2025.0810.220.3
Naive RAGModel Family=Llama-3.1-8B-Instruct2026.049.8—
ParaSet+SetCEAugmentation=∪ CE2026.079.315.7
LLM2026.079.114.3
SetCE2026.07916.2
CE2026.078.515.9
BM25Inference LLM=Gemini-2.5-flash2025.087.910.7
Naive GenerationModel Family=Mistral-7B-Instruct2026.047.7—
ParaSet+SetCE2026.077.314.1
Naive GenerationModel Family=Llama-3.1-8B-Instruct2026.044.4—
ZEROSHOTLLM=Qwen3-30B-A3B2026.052.39.4