Gamma Sampling: Fine-grained Controlling Language Models without Training

The dominant approaches for controlling language models achieve prominence in controlling high-level attributes (e.g. topic and sentiment). However, these methods often require condition-specific data or are computationally expensive. We propose a new simple guided decoding method, Gamma Sampling, which does not require any training data to achieve fine-grained controllable text generation while maintaining a fast generation speed. Gamma Sampling introduces attribute-related information (provided by humans or language models themselves) into the sampling process to guide language models to generate texts with desired attributes. Since no training is involved, Gamma Sampling can be easily applied to any language model for controllable text generation. Through experiments, we show that Gamma Sampling-steered GPT2-small (117M) outperforms baselines such as PPLM (345M) and CTRL (1.6B) in diversity, attribute relevance, and overall quality of generated samples.Comment: 20 pages, 5 figure