A Lightweight Multi Aspect Controlled Text Generation Solution For Large Language Models
This work addresses the challenge of enabling LLMs to perform MCTG tasks without extensive instruction tuning, though it is incremental as it builds on data augmentation methods.
The paper tackles the problem of multi-aspect controllable text generation (MCTG) in large language models (LLMs) by proposing a lightweight data augmentation pipeline to address biases and correlations in existing datasets, resulting in a 20% accuracy improvement and reduced aspect correlations.
Large language models (LLMs) show remarkable abilities with instruction tuning. However, they fail to achieve ideal tasks when lacking high-quality instruction tuning data on target tasks. Multi-Aspect Controllable Text Generation (MCTG) is a representative task for this dilemma, where aspect datasets are usually biased and correlated. Existing work exploits additional model structures and strategies for solutions, limiting adaptability to LLMs. To activate MCTG ability of LLMs, we propose a lightweight MCTG pipeline based on data augmentation. We analyze bias and correlations in traditional datasets, and address these concerns with augmented control attributes and sentences. Augmented datasets are feasible for instruction tuning. In our experiments, LLMs perform better in MCTG after data augmentation, with a 20% accuracy rise and less aspect correlations.