MixCE: Training Autoregressive Language Models by Mixing Forward and Reverse Cross-Entropies

Shiyue Zhang, Shijie Wu, Ozan Irsoy, Steven Lu, Mohit Bansal, Mark Dredze, David Rosenberg


Abstract
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.
Anthology ID:
2023.acl-long.502
Volume:
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
Month:
July
Year:
2023
Address:
Toronto, Canada
Editors:
Anna Rogers, Jordan Boyd-Graber, Naoaki Okazaki
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
9027–9050
Language:
URL:
https://aclanthology.org/2023.acl-long.502
DOI:
10.18653/v1/2023.acl-long.502
Bibkey:
Cite (ACL):
Shiyue Zhang, Shijie Wu, Ozan Irsoy, Steven Lu, Mohit Bansal, Mark Dredze, and David Rosenberg. 2023. MixCE: Training Autoregressive Language Models by Mixing Forward and Reverse Cross-Entropies. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 9027–9050, Toronto, Canada. Association for Computational Linguistics.
Cite (Informal):
MixCE: Training Autoregressive Language Models by Mixing Forward and Reverse Cross-Entropies (Zhang et al., ACL 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.acl-long.502.pdf
Video:
 https://aclanthology.org/2023.acl-long.502.mp4