C-ICL: Contrastive In-context Learning for Information Extraction

TL;DR

This paper introduces c-ICL, a novel few-shot learning technique for information extraction that leverages both correct and incorrect examples to improve LLM performance in NER and RE tasks.

Contribution

The paper proposes a new in-context learning method that incorporates negative samples and reasoning to enhance information extraction capabilities of LLMs.

Findings

c-ICL outperforms previous few-shot methods in various datasets

Incorporating negative samples improves extraction accuracy

Method demonstrates versatility across multiple IE tasks

Abstract

There has been increasing interest in exploring the capabilities of advanced large language models (LLMs) in the field of information extraction (IE), specifically focusing on tasks related to named entity recognition (NER) and relation extraction (RE). Although researchers are exploring the use of few-shot information extraction through in-context learning with LLMs, they tend to focus only on using correct or positive examples for demonstration, neglecting the potential value of incorporating incorrect or negative examples into the learning process. In this paper, we present c-ICL, a novel few-shot technique that leverages both correct and incorrect sample constructions to create in-context learning demonstrations. This approach enhances the ability of LLMs to extract entities and relations by utilizing prompts that incorporate not only the positive samples but also the reasoning behind them. This method allows for the identification and correction of potential interface errors. Specifically, our proposed method taps into the inherent contextual information and valuable information in hard negative samples and the nearest positive neighbors to the test and then applies the in-context learning demonstrations based on LLMs. Our experiments on various datasets indicate that c-ICL outperforms previous few-shot in-context learning methods, delivering substantial enhancements in performance across a broad spectrum of related tasks. These improvements are noteworthy, showcasing the versatility of our approach in miscellaneous scenarios.