Autoregressive language models are trained by minimizing the cross-entropy of the model distribution Q relative to the data distribution P -- that is, minimizing the forward cross-entropy, which is equivalent to maximum likelihood estimation (MLE). We have observed that models trained in this way may "over-generalize", in the sense that they produce non-human-like text. Moreover, we believe that reverse cross-entropy, i.e., the cross-entropy of P relative to Q, is a better reflection of how a human would evaluate text generated by a model. Hence, we propose learning with MixCE, an objective that mixes the forward and reverse cross-entropies. We evaluate models trained with this objective on synthetic data settings (where P is known) and real data, and show that the resulting models yield better generated text without complex decoding strategies. Our code and models are publicly available at https://github.com/bloomberg/mixce-acl2023
@article{arxiv.2305.16958,
title = {MixCE: Training Autoregressive Language Models by Mixing Forward and Reverse Cross-Entropies},
author = {Shiyue Zhang and Shijie Wu and Ozan Irsoy and Steven Lu and Mohit Bansal and Mark Dredze and David Rosenberg},
journal= {arXiv preprint arXiv:2305.16958},
year = {2024}
}