RAG4RE

Reported on 4 benchmarks across 1 task · 1 paper · 2 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Natural Language Processing4 results

Relation ExtractiononTACRED
F1· 2024-04-20
86.6
SOTA
Retrieval-Augmented Generation-based Relation Extraction arXiv:2404.13397
Relation ExtractiononTACRED-Revisited
F1· 2024-04-20
88.3
SOTA
Retrieval-Augmented Generation-based Relation Extraction arXiv:2404.13397
Relation ExtractiononSemEval-2010 Task 8
F1· 2024-04-20
23.41
best: 43.5 (LLM-QA4RE (XXLarge))
Retrieval-Augmented Generation-based Relation Extraction arXiv:2404.13397
Relation ExtractiononRe-TACRED
F1· 2024-04-20
73.3
best: 91.4 (EXOBRAIN)
Retrieval-Augmented Generation-based Relation Extraction arXiv:2404.13397