A Factuality and Diversity Reconciled Decoding Method for Knowledge-Grounded Dialogue Generation
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866908499571638272 |
|---|---|
| author | Yang, Chenxu Lin, Zheng Tian, Chong Pang, Liang Wang, Lanrui Tong, Zhengyang Ho, Qirong Cao, Yanan Wang, Weiping |
| author_facet | Yang, Chenxu Lin, Zheng Tian, Chong Pang, Liang Wang, Lanrui Tong, Zhengyang Ho, Qirong Cao, Yanan Wang, Weiping |
| contents | Grounding external knowledge can enhance the factuality of responses in dialogue generation. However, excessive emphasis on it might result in the lack of engaging and diverse expressions. Through the introduction of randomness in sampling, current approaches can increase the diversity. Nevertheless, such sampling method could undermine the factuality in dialogue generation. In this study, to discover a solution for advancing creativity without relying on questionable randomness and to subtly reconcile the factuality and diversity within the source-grounded paradigm, a novel method named DoGe is proposed. DoGe can dynamically alternate between the utilization of internal parameter knowledge and external source knowledge based on the model's factual confidence. Extensive experiments on three widely-used datasets show that DoGe can not only enhance response diversity but also maintain factuality, and it significantly surpasses other various decoding strategy baselines. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_05718 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | A Factuality and Diversity Reconciled Decoding Method for Knowledge-Grounded Dialogue Generation Yang, Chenxu Lin, Zheng Tian, Chong Pang, Liang Wang, Lanrui Tong, Zhengyang Ho, Qirong Cao, Yanan Wang, Weiping Computation and Language Grounding external knowledge can enhance the factuality of responses in dialogue generation. However, excessive emphasis on it might result in the lack of engaging and diverse expressions. Through the introduction of randomness in sampling, current approaches can increase the diversity. Nevertheless, such sampling method could undermine the factuality in dialogue generation. In this study, to discover a solution for advancing creativity without relying on questionable randomness and to subtly reconcile the factuality and diversity within the source-grounded paradigm, a novel method named DoGe is proposed. DoGe can dynamically alternate between the utilization of internal parameter knowledge and external source knowledge based on the model's factual confidence. Extensive experiments on three widely-used datasets show that DoGe can not only enhance response diversity but also maintain factuality, and it significantly surpasses other various decoding strategy baselines. |
| title | A Factuality and Diversity Reconciled Decoding Method for Knowledge-Grounded Dialogue Generation |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2407.05718 |