可控数据增强：基于思维链属性操作的少样本文本挖掘
Controllable Data Augmentation for Few-Shot Text Mining with Chain-of-Thought Attribute Manipulation
AI总结：
提出CoTAM方法，通过思维链属性操作在少样本文本挖掘中实现可控数据增强，在多项任务上优于其他LLM增强方法。
摘要：
近年来，提示大型语言模型（LLM）进行数据增强已成为少样本自然语言处理任务中的常见做法。在本文中，我们提出了思维链属性操作（CoTAM），一种新颖的方法，该方法仅通过调整用户提供的、任务特定的属性（例如电影评论中的情感极性或主题）即可从现有示例生成新数据。与传统潜在表示控制不同，我们利用思维链提示直接以三个步骤编辑文本：（1）属性分解，（2）操作提议，以及（3）句子重构。在多种任务上的广泛结果，如文本（对）分类、基于方面的情感分析和条件文本生成，验证了CoTAM在相同数量的训练示例下，对于微调和上下文学习均优于其他基于LLM的增强方法。值得注意的是，使用主成分分析对增强数据集进行的二维可视化揭示了人类可识别的决策边界，这很可能由属性操作所暗示，展示了我们提出的方法的潜力。
英文摘要：
Prompting large language models (LLMs) for data augmentation has recently become a common practice in few-shot NLP tasks. In this paper, we propose Chain-of-Thought Attribute Manipulation (CoTAM), a novel approach that generates new data from existing examples by only tweaking in the user-provided, task-specific attribute, e.g., sentiment polarity or topic in movie reviews. Instead of conventional latent representation controlling, we leverage the chain-of-thought prompting to directly edit the text in three steps, (1) attribute decomposition, (2) manipulation proposal, and (3) sentence reconstruction. Extensive results on various tasks, such as text (pair) classification, aspect-based sentiment analysis, and conditional text generation, verify the superiority of CoTAM over other LLM-based augmentation methods with the same number of training examples for both fine-tuning and in-context learning. Remarkably, the 2D visualization of the augmented dataset using principal component analysis revealed a human-recognizable decision boundary that is likely hinted by the attribute manipulation, demonstrating the potential of our proposed approach.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
