Abstract
Existing knowledge-grounded open-domain dialogue generation models often face the hallucination problem, i.e. the dialogue generative model will persist in an inappropriate knowledge and generate responses that inconsistent with the facts. We argue that this problem mainly stems from the polarized optimization objectives and weak knowledge generation ability. To mitigate the hallucination, we take inspiration from human communicating that people will replay euphemistic responses for the unclear or unrecognizable knowledge, and propose an Augmentative and Contrastive Knowledge Dialogue Expansion Framework (ACK-DEF). ACK-DEF constructs the augmentative and contrastive knowledge dialogue samples, which consist of the knowledge of different degrees of errors and the response of manual design, to expand the original training set and smooth the polarized optimization objective that enables models to generate ground-truth with or without gold knowledge. Not only the knowledge, ACK-DEF also provides the tactful responses of manual design corresponding to the incomplete correct knowledge. Experimental results on the Wikipedia of Wizard dataset show that employing the ACK-DEF is effective to alleviate the hallucination problem.- Anthology ID:
- 2023.acl-short.148
- Volume:
- Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 2: Short 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:
- 1741–1750
- Language:
- URL:
- https://aclanthology.org/2023.acl-short.148
- DOI:
- 10.18653/v1/2023.acl-short.148
- Cite (ACL):
- Bin Sun, Yitong Li, Fei Mi, Fanhu Bie, Yiwei Li, and Kan Li. 2023. Towards Fewer Hallucinations in Knowledge-Grounded Dialogue Generation via Augmentative and Contrastive Knowledge-Dialogue. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pages 1741–1750, Toronto, Canada. Association for Computational Linguistics.
- Cite (Informal):
- Towards Fewer Hallucinations in Knowledge-Grounded Dialogue Generation via Augmentative and Contrastive Knowledge-Dialogue (Sun et al., ACL 2023)
- PDF:
- https://preview.aclanthology.org/improve-issue-templates/2023.acl-short.148.pdf