Aligning Instruction Tasks Unlocks Large Language Models as Zero-Shot Relation Extractors

Open paper
Benchmark Model Rank Results
relation-extraction-on-re-tacredLLM-QA4RE (XXLarge)#8F1: 66.5
relation-extraction-on-tacredLLM-QA4RE (XXLarge)#34F1: 52.2
relation-extraction-on-tacred-revisitedLLM-QA4RE (XXLarge)#2F1: 53.4

Rank counts only results with a code link.