October 31, 2018
Current dialogue systems fail at being engaging for users, especially when trained endto-end without relying on proactive reengaging scripted strategies. Zhang et al. (2018) showed that the engagement level of end-toend dialogue models increases when conditioning them on text personas providing some personalized back-story to the model. However, the dataset used in (Zhang et al., 2018) is synthetic and only contains around 1k different personas. In this paper we introduce a new dataset providing 5 million personas and 700 million persona-based dialogues. Our experiments show that, at this scale, training using personas still improves the performance of end-to-end systems. In addition, we show that other tasks benefit from the wide coverage of our dataset by fine-tuning our model on the data from (Zhang et al., 2018) and achieving state-of-the-art results.
Written by
Pierre-Emmanuel Mazaré
Antoine Bordes
Martin Raison
Samuel Humeau
Publisher
EMNLP
July 17, 2026
Zilin Xiao, Qi Ma, Jason Chen, Xintao Chen, Avinash Atreya, Hanjie Chen, Vicente Ordonez
July 17, 2026
July 13, 2026
Xiaodong Wang, Xuanyi Zhao, Pedro Rodriguez, Devendra Singh Sachan, Barlas Oguz, Seungwhan Moon, Shang-Wen Li, Gargi Ghosh, Xin Dong, Wen-Tau Yih
July 13, 2026
July 03, 2026
Sonia Joseph, Quentin Garrido, Randall Balestriero, Matthew Kowal, Thomas Fel, Shahab Bakhtiari, Blake Richards, Mike Rabbat
July 03, 2026
June 05, 2026
Zeyu Yang, Qi Ma, Jason Chen, Anshumali Shrivastava
June 05, 2026

Our approach
Latest news
Foundational models