Plug and Play with Prompts: A Prompt Tuning Approach for Controlling Text Generation

Abstract: Transformer-based LLMs have shown exceptional language generation capabilities in response to text-based prompts. However, controlling the direction of generation via textual prompts has been challenging, especially with smaller models. In this work, we explore the use of Prompt Tuning to achieve controlled language generation. Generated text is steered using prompt embeddings, which are trained using a small LLM, used as a discriminator. Moreover, we demonstrate that these prompt embeddings can be trained with a very small dataset, with as low as a few hundred training examples. Our method thus offers a data and parameter efficient solution towards controlling LLM outputs. We carry out extensive evaluation on four datasets: SST-5 and Yelp (sentiment analysis), GYAFC (formality) and JIGSAW (toxic language). Finally, we demonstrate the efficacy of our method towards mitigating harmful, toxic, and biased text generated by LLMs.