# Controllable Data Augmentation for Few-Shot Text Mining with Chain-of-Thought Attribute Manipulation

arXiv: https://arxiv.org/abs/2307.07099 · HTML: https://mlsanity.com/paper/2307.07099/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Placed in Prompting and chain-of-thought reasoning, one of 17 directions in LLM reasoning.
- Builds on 11 of its 45 references that are in the map.
- First posted on arXiv 14 Jul 2023.

## Placed in

- LLM reasoning / [Prompting and chain-of-thought reasoning](https://mlsanity.com/lr/prompting-and-chain-of-thought-reasoning/)

## Builds on (most cited first, 11 of 11)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [PaLM: Scaling Language Modeling with Pathways](https://mlsanity.com/paper/2204.02311/) (2022)
- [Emergent Abilities of Large Language Models](https://mlsanity.com/paper/2206.07682/) (2022)
- [A Survey on In-context Learning](https://mlsanity.com/paper/2301.00234/) (2022)
- [GPT3Mix: Leveraging Large-scale Language Models for Text Augmentation](https://mlsanity.com/paper/2104.08826/) (2021)
- [Invertible Conditional GANs for image editing](https://mlsanity.com/paper/1611.06355/) (2016)
- [Goal-Driven Explainable Clustering via Language Descriptions](https://mlsanity.com/paper/2305.13749/) (2023)
- [LLM-powered Data Augmentation for Enhanced Cross-lingual Performance](https://mlsanity.com/paper/2305.14288/) (2023)
- [Data Augmentation for Intent Classification with Off-the-shelf Large Language Models](https://mlsanity.com/paper/2204.01959/) (2022)
- [Improving Contrastive Learning of Sentence Embeddings from AI Feedback](https://mlsanity.com/paper/2305.01918/) (2023)

## Built on by (most cited first, 9 of 9)

- [Answer is All You Need: Instruction-following Text Embedding via Answering the Question](https://mlsanity.com/paper/2402.09642/) (2024)
- [User Modeling in the Era of Large Language Models: Current Research and Future Directions](https://mlsanity.com/paper/2312.11518/) (2023)
- [Exploring Empty Spaces: Human-in-the-Loop Data Augmentation](https://mlsanity.com/paper/2410.01088/) (2024)
- [Persona-Based Synthetic Data Generation Using Multi-Stage Conditioning with Large Language Models for Emotion Recognition](https://mlsanity.com/paper/2507.13380/) (2025)
- [Enhancing Effectiveness and Robustness in a Low-Resource Regime via Decision-Boundary-aware Data Augmentation](https://mlsanity.com/paper/2403.15512/) (2024)
- [DSAI: Unbiased and Interpretable Latent Feature Extraction for Data-Centric AI](https://mlsanity.com/paper/2412.06303/) (2024)
- [Enhancing Granular Sentiment Classification with Chain-of-Thought Prompting in Large Language Models](https://mlsanity.com/paper/2505.04135/) (2025)
- [Class-Structure Preservation Beats Diversity: A Comprehensive Benchmark of Text Augmentation Methods for Imbalanced Text Classification](https://mlsanity.com/paper/2608.12340/) (2026)
- [DualGuard: Dual-Mode Quality Control for Logic-Preserving Data Augmentation](https://mlsanity.com/paper/2609.32431/) (2026)

## Abstract (arXiv)

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.