DExperts: Decoding-Time Controlled Text Generation with Experts and Anti-Experts

Understand

Despite recent advances in natural language generation, it remains challenging to control attributes of generated text.

• We propose DExperts: Decoding-time Experts, a decoding-time method for controlled text generation that combines a pretrained language model with "expert" LMs and/or "anti-expert" LMs in a product of experts.
• Intuitively, under the ensemble, tokens only get high probability if they are considered likely by the experts, and unlikely by the anti-experts.
• We apply DExperts to language detoxification and sentiment-controlled generation, where we outperform existing controllable generation methods on both automatic and human evaluations.