In this paper, we propose a novel method, Chain-of-Thoughts Attribute Manipulation (CoTAM), to guide few-shot learning by carefully crafted data from Large Language Models (LLMs). The main idea is to create data with changes only in the attribute targeted by the task. Inspired by facial attribute manipulation, our approach generates label-switched data by leveraging LLMs to manipulate task-specific attributes and reconstruct new sentences in a controlled manner. Instead of conventional latent representation controlling, we implement chain-of-thoughts decomposition and reconstruction to adapt the procedure to LLMs. Extensive results on text classification and other tasks verify the advantage of CoTAM over other LLM-based text generation methods with the same number of training examples. Analysis visualizes the attribute manipulation effectiveness of CoTAM and presents the potential of LLM-guided learning with even less supervision.

翻译：本文提出一种新方法——链式思维属性操控（CoTAM），通过大型语言模型（LLMs）精心构造的数据来引导少样本学习。核心思想是创建仅针对任务目标属性发生改变的数据。受面部属性操控启发，该方法利用LLMs操控特定任务属性，并以受控方式重构新句子，从而生成标签翻转数据。不同于传统的隐表示控制，我们采用链式思维分解与重构，使流程适配LLMs。在文本分类等多种任务上的大量实验结果验证了，在训练样本数量相同的情况下，CoTAM优于其他基于LLM的文本生成方法。分析可视化展示了CoTAM的属性操控有效性，并揭示了在更少监督条件下进行LLM引导学习的潜力。