针对法律文本分类中罕见类别表现差的问题，提出有选择地增强低频样本。
Exploring Selective Retrieval-Augmentation for Long-Tail Legal Text Classification
- 仅对训练集中低频标签样本进行检索增强，避免噪声干扰
- 在LEDGAR和UNFAIR-ToS上均提升微平均与宏平均F1
- 无需修改模型结构，不依赖外部数据，适合法律领域小样本场景
法律文本分类是法律领域的一项基础NLP任务。该领域的基准数据集通常呈现长尾标签分布，许多标签样本稀少，导致模型在罕见类别上表现不佳。本文探索了选择性检索增强（Selective Retrieval-Augmentation, SRA）作为解决方案的可行性。SRA仅对训练集中低频标签的样本进行增强，避免对高频率类引入噪声，且无需修改模型架构。检索仅从训练数据中进行，防止信息泄露，无需依赖外部语料库。在两个具有长尾分布的法律文本分类基准数据集LEDGAR（单标签）和UNFAIR-ToS（多标签）上测试，结果表明SRA在micro-F1和macro-F1上均优于LexGLUE基线。
原文摘要 · Abstract (English)
Legal text classification is a fundamental NLP task in the legal domain. Benchmark datasets in this area often exhibit a long-tail label distribution, where many labels are underrepresented, leading to poor model performance on rare classes. This paper explores Selective Retrieval-Augmentation (SRA) as a proof-of-concept approach to this problem. SRA focuses on augmenting samples belonging to low-frequency labels in the training set, preventing the introduction of noise for well-represented classes, and requires no changes to the model architecture. Retrieval is performed only from the training data to ensure there is no potential information leakage, removing the need for external corpora simultaneously. SRA is tested on two legal text classification benchmark datasets with long-tail distributions: LEDGAR (single-label) and UNFAIR-ToS (multi-label). Results show that SRA achieves consistent gains in both micro-F1 and macro-F1 over LexGLUE baselines.
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。