Towards Boosting the Open-Domain Chatbot with Human Feedback

Hua Lu, Siqi Bao, Huang He, Fan Wang, Hua Wu, Haifeng Wang


Abstract
Many open-domain dialogue models pre-trained with social media comments can generate coherent replies but have difficulties producing engaging responses. This phenomenon might mainly result from the deficiency of annotated human-human conversations and the misalignment with human preference. In this paper, we propose a novel and efficient framework Diamante to boost the open-domain chatbot, where two kinds of human feedback (including explicit demonstration and implicit preference) are collected and leveraged. By asking annotators to select or amend the model-generated candidate responses, Diamante efficiently collects the human demonstrated responses and constructs a Chinese chit-chat dataset. To enhance the alignment with human preference, Diamante leverages the implicit preference in the data collection process and introduces the generation-evaluation joint training. Comprehensive experiments indicate that the Diamante dataset and joint training paradigm can significantly boost the performance of pre-trained dialogue models. The overall engagingness of the previous state-of-the-art model has been improved remarkably by 50% in Chinese open-domain conversations.
Anthology ID:
2023.acl-long.224
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:
4060–4078
Language:
URL:
https://aclanthology.org/2023.acl-long.224
DOI:
10.18653/v1/2023.acl-long.224
Bibkey:
Cite (ACL):
Hua Lu, Siqi Bao, Huang He, Fan Wang, Hua Wu, and Haifeng Wang. 2023. Towards Boosting the Open-Domain Chatbot with Human Feedback. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 4060–4078, Toronto, Canada. Association for Computational Linguistics.
Cite (Informal):
Towards Boosting the Open-Domain Chatbot with Human Feedback (Lu et al., ACL 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.acl-long.224.pdf
Video:
 https://aclanthology.org/2023.acl-long.224.mp4