Chain of Thought with Explicit Evidence Reasoning for Few-shot Relation Extraction

TL;DR

This paper introduces CoT-ER, a novel method using large language models to explicitly generate and incorporate evidence in chain-of-thought prompts, significantly improving few-shot relation extraction without training.

Contribution

The paper proposes a new approach that explicitly models evidence reasoning in chain-of-thought prompts for few-shot relation extraction using large language models.

Findings

CoT-ER achieves competitive results with fully-supervised methods.

The approach requires no training data to perform well.

Explicit evidence reasoning enhances relation extraction accuracy.

Abstract

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 in-context learning has been demonstrating notable results without the need of training. Few studies have already utilized in-context learning for zero-shot 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 evidences using task-specific and concept-level knowledge. Then these evidences are 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.