Despite recent advances in natural language generation, it remains challenging to control attributes of generated text. We propose DEX-PERTS: Decoding-time Experts, a decodingtime 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. Moreover, because DEXPERTS operates only on the output of the pretrained LM, it is effective with (anti-)experts of smaller size, including when operating on GPT-3. Our work highlights the promise of tuning small LMs on text with (un)desirable attributes for efficient decoding-time steering.

No abstract

No abstract

No abstract

The common practice for training commonsense models has gone from-human-to-corpusto-machine: humans author commonsense knowledge graphs in order to train commonsense models. In this work, we investigate an alternative, from-machine-to-corpus-tomachine: general language models author these commonsense knowledge graphs to train commonsense models.Our study leads to a new framework, Symbolic Knowledge Distillation. As with prior art in Knowledge Distillation (Hinton et al., 2015), our approach uses larger models to teach smaller models. A key difference is that we distill knowledge symbolically-as text-in addition to the resulting neural model. We distill only one aspect-the commonsense of a general language model teacher, allowing the student to be a different type of model, a commonsense model. Altogether, we show that careful prompt engineering and a separately trained critic model allow us to selectively distill highquality causal commonsense from GPT-3, a general language model. Empirical results demonstrate that, for the first time, a human-authored commonsense knowledge graph is surpassed by our automatically distilled variant in all three criteria: quantity, quality, and diversity. In addition, it results in a neural commonsense model that surpasses the teacher model's commonsense capabilities despite its 100x smaller size. We apply this to the ATOMIC resource, and will share our new symbolic knowledge graph and commonsense models 1 .