CMD: a framework for Context-aware Model self-Detoxification

Zecheng Tang, Keyan Zhou, Juntao Li, Yuyang Ding, Pinzheng Wang, Yan Bowen, Renjie Hua, Min Zhang


Abstract
Text detoxification aims to minimize the risk of language models producing toxic content. Existing detoxification methods of directly constraining the model output or further training the model on the non-toxic corpus fail to achieve a decent balance between detoxification effectiveness and generation quality. This issue stems from the neglect of constrain imposed by the context since language models are designed to generate output that closely matches the context while detoxification methods endeavor to ensure the safety of the output even if it semantically deviates from the context. In view of this, we introduce a Context-aware Model self-Detoxification (CMD) framework that pays attention to both the context and the detoxification process, i.e., first detoxifying the context and then making the language model generate along the safe context. Specifically, CMD framework involves two phases: utilizing language models to synthesize data and applying these data for training. We also introduce a toxic contrastive loss that encourages the model generation away from the negative toxic samples. Experiments on various LLMs have verified the effectiveness of our MSD framework, which can yield the best performance compared to baselines.
Anthology ID:
2024.emnlp-main.115
Volume:
Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing
Month:
November
Year:
2024
Address:
Miami, Florida, USA
Editors:
Yaser Al-Onaizan, Mohit Bansal, Yun-Nung Chen
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1930–1949
Language:
URL:
https://aclanthology.org/2024.emnlp-main.115
DOI:
Bibkey:
Cite (ACL):
Zecheng Tang, Keyan Zhou, Juntao Li, Yuyang Ding, Pinzheng Wang, Yan Bowen, Renjie Hua, and Min Zhang. 2024. CMD: a framework for Context-aware Model self-Detoxification. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 1930–1949, Miami, Florida, USA. Association for Computational Linguistics.
Cite (Informal):
CMD: a framework for Context-aware Model self-Detoxification (Tang et al., EMNLP 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.emnlp-main.115.pdf