Chain of Thought with Explicit Evidence Reasoning for Few-shot Relation Extraction
Xilai Ma, Jing Li, Min Zhang · 2023
Few-shot relation extraction involves identifying the type of relationship between two specific entities within a text, using a limited number of annotated samples.A variety of solutions to this problem have emerged by applying meta-learning and neural graph techniques which typically necessitate a training process for adaptation.Recently, the strategy of incontext learning has been demonstrating notable results without training.Few studies have already utilized in-context learning for zeroshot information extraction.Unfortunately, the evidence for inference is either not considered or implicitly modeled during the construction of chain-of-thought prompts.In this paper, we propose a novel approach for few-shot relation extraction using large language models, named CoT-ER, chain-of-thought with explicit evidence reasoning.In particular, CoT-ER first induces large language models to generate evidence using task-specific and concept-level knowledge.Then this evidence is explicitly incorporated into chain-of-thought prompting for relation extraction.Experimental results demonstrate that our CoT-ER approach (with 0% training data) achieves competitive performance compared to the fully-supervised (with 100% training data) state-of-the-art approach on the FewRel1.0 and FewRel2.0 datasets.