LiFi: Lightweight Controlled Text Generation with Fine-Grained Control Codes

Understand

In the rapidly evolving field of text generation, the demand for more precise control mechanisms has become increasingly apparent.

• To address this need, we present a novel methodology, LIFI, which offers a lightweight approach with fine-grained control for controlled text generation.
• Unlike previous studies that train pre-trained language models to follow discrete, categorical, and exclusive control codes, LIFI learns controlled text generation under the guidance of continuous, relative, and nonexclusive control codes.
• These fine-grained codes are automatically derived from an attribute classifier, initially trained with a small amount of labeled data and subsequently employed to label abundant unlabeled data, thus garnering more extensive supervision signals.