EL4NER: Ensemble Learning for Named Entity Recognition via Multiple Small-Parameter Large Language Models

TL;DR

EL4NER introduces an ensemble learning approach that combines multiple small-parameter open-source LLMs with advanced techniques to improve NER performance efficiently, reducing reliance on large models.

Contribution

The paper presents a novel ensemble learning framework for NER that leverages multiple small LLMs, incorporating task decomposition, span-level similarity retrieval, and self-validation.

Findings

EL4NER outperforms most large-parameter LLM-based methods on several NER datasets.

It achieves state-of-the-art results among ICL-based methods in certain cases.

The approach demonstrates high parameter efficiency and practicality for NER tasks.

Abstract

In-Context Learning (ICL) technique based on Large Language Models (LLMs) has gained prominence in Named Entity Recognition (NER) tasks for its lower computing resource consumption, less manual labeling overhead, and stronger generalizability. Nevertheless, most ICL-based NER methods depend on large-parameter LLMs: the open-source models demand substantial computational resources for deployment and inference, while the closed-source ones incur high API costs, raise data-privacy concerns, and hinder community collaboration. To address this question, we propose an Ensemble Learning Method for Named Entity Recognition (EL4NER), which aims at aggregating the ICL outputs of multiple open-source, small-parameter LLMs to enhance overall performance in NER tasks at less deployment and inference cost. Specifically, our method comprises three key components. First, we design a task decomposition-based pipeline that facilitates deep, multi-stage ensemble learning. Second, we introduce a novel span-level sentence similarity algorithm to establish an ICL demonstration retrieval mechanism better suited for NER tasks. Third, we incorporate a self-validation mechanism to mitigate the noise introduced during the ensemble process. We evaluated EL4NER on multiple widely adopted NER datasets from diverse domains. Our experimental results indicate that EL4NER surpasses most closed-source, large-parameter LLM-based methods at a lower parameter cost and even attains state-of-the-art (SOTA) performance among ICL-based methods on certain datasets. These results show the parameter efficiency of EL4NER and underscore the feasibility of employing open-source, small-parameter LLMs within the ICL paradigm for NER tasks.