提升大模型在少样本实体识别中的边界感知与跨域适应能力
BANER: Boundary-Aware LLMs for Few-Shot Named Entity Recognition
- 引入边界感知对比学习，增强模型对实体边界的识别能力
- 通过LoRAHub实现跨域信息对齐，提升分类泛化性能
- 适用于多种大模型架构，实验验证效果显著优于基线
尽管两阶段原型网络在少样本命名实体识别中取得进展，但实体跨度检测阶段仍存在过检/漏检问题，类型分类阶段则存在实体原型不匹配。此外，大模型在通用少样本信息抽取任务中表现不佳。本文提出边界感知大模型（BANER），通过边界感知对比学习提升大模型对实体边界的感知能力；并利用LoRAHub将目标域信息对齐到源域，增强跨域分类适应性。在多个基准测试上的大量实验表明，该框架超越现有方法，且在不同大模型架构下均具有效性。代码与数据已公开于https://github.com/UESTC-GQJ/BANER。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。