用课程式数据增强提升开源大模型的隐喻检测效果
Curriculum-style Data Augmentation for LLM-based Metaphor Detection
- 先筛选正确预测样本，错例做数据增强种子
- 仅一次推理就达到领先性能，降低延迟和成本
- 适合资源有限但需高效隐喻识别的研究者
近期利用大语言模型（LLMs）进行隐喻检测取得了良好效果。然而，这些方法严重依赖闭源LLMs，带来较高的推理成本与延迟。为此，我们提出一种通过微调开源LLMs实现隐喻检测的方法，在单次推理下有效降低计算成本与延迟。此外，隐喻检测面临严重的数据稀缺问题，阻碍了LLMs的有效微调。为此，我们引入课程式数据增强（CDA）：在微调前评估训练数据，将正确预测样本用于微调，错误预测样本作为数据增强的种子。该方法使模型先学习简单知识，再逐步掌握复杂知识，从而实现性能的渐进提升。实验表明，该方法在所有基线中均达到最优表现。我们还进行了详细的消融实验，验证了CDA的有效性。
原文摘要 · Abstract (English)
Recently, utilizing large language models (LLMs) for metaphor detection has achieved promising results. However, these methods heavily rely on the capabilities of closed-source LLMs, which come with relatively high inference costs and latency. To address this, we propose a method for metaphor detection by fine-tuning open-source LLMs, effectively reducing inference costs and latency with a single inference step. Furthermore, metaphor detection suffers from a severe data scarcity problem, which hinders effective fine-tuning of LLMs. To tackle this, we introduce Curriculum-style Data Augmentation (CDA). Specifically, before fine-tuning, we evaluate the training data to identify correctly predicted instances for fine-tuning, while incorrectly predicted instances are used as seed data for data augmentation. This approach enables the model to quickly learn simpler knowledge and progressively acquire more complex knowledge, thereby improving performance incrementally. Experimental results demonstrate that our method achieves state-of-the-art performance across all baselines. Additionally, we provide detailed ablation studies to validate the effectiveness of CDA.
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。