DetoxLLM: A Framework for Detoxification with Explanations

Md Tawkat Islam Khondaker, Muhammad Abdul-Mageed, Laks Lakshmanan


Abstract
Prior works on detoxification are scattered in the sense that they do not cover all aspects of detoxification needed in a real-world scenario. Notably, prior works restrict the task of developing detoxification models to only a seen subset of platforms, leaving the question of how the models would perform on unseen platforms unexplored. Additionally, these works do not address non-detoxifiability, a phenomenon whereby the toxic text cannot be detoxified without altering the meaning. We propose DetoxLLM, the first comprehensive end-to-end detoxification framework, which attempts to alleviate the aforementioned limitations. We first introduce a cross-platform pseudo-parallel corpus applying multi-step data processing and generation strategies leveraging ChatGPT. We then train a suite of detoxification models with our cross-platform corpus. We show that our detoxification models outperform the SoTA model trained with human-annotated parallel corpus. We further introduce explanation to promote transparency and trustworthiness. DetoxLLM additionally offers a unique paraphrase detector especially dedicated for the detoxification task to tackle the non-detoxifiable cases. Through experimental analysis, we demonstrate the effectiveness of our cross-platform corpus and the robustness of DetoxLLM against adversarial toxicity.
Anthology ID:
2024.emnlp-main.1066
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:
19112–19139
Language:
URL:
https://aclanthology.org/2024.emnlp-main.1066
DOI:
Bibkey:
Cite (ACL):
Md Tawkat Islam Khondaker, Muhammad Abdul-Mageed, and Laks Lakshmanan. 2024. DetoxLLM: A Framework for Detoxification with Explanations. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 19112–19139, Miami, Florida, USA. Association for Computational Linguistics.
Cite (Informal):
DetoxLLM: A Framework for Detoxification with Explanations (Khondaker et al., EMNLP 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.emnlp-main.1066.pdf