BANER: Boundary-Aware LLMs for Few-Shot Named Entity Recognition

TL;DR

This paper introduces BANER, a boundary-aware approach using contrastive learning and domain adaptation techniques to improve few-shot named entity recognition with large language models, achieving superior performance across benchmarks.

Contribution

The paper presents a novel boundary-aware contrastive learning strategy and domain alignment method for LLMs, significantly enhancing few-shot NER performance.

Findings

Outperforms prior methods on various benchmarks

Effective across multiple LLM architectures

Improves entity boundary perception and cross-domain classification

Abstract

Despite the recent success of two-stage prototypical networks in few-shot named entity recognition (NER), challenges such as over/under-detected false spans in the span detection stage and unaligned entity prototypes in the type classification stage persist. Additionally, LLMs have not proven to be effective few-shot information extractors in general. In this paper, we propose an approach called Boundary-Aware LLMs for Few-Shot Named Entity Recognition to address these issues. We introduce a boundary-aware contrastive learning strategy to enhance the LLM's ability to perceive entity boundaries for generalized entity spans. Additionally, we utilize LoRAHub to align information from the target domain to the source domain, thereby enhancing adaptive cross-domain classification capabilities. Extensive experiments across various benchmarks demonstrate that our framework outperforms prior methods, validating its effectiveness. In particular, the proposed strategies demonstrate effectiveness across a range of LLM architectures. The code and data are released on https://github.com/UESTC-GQJ/BANER.