LLM-based Rewriting of Inappropriate Argumentation using Reinforcement Learning from Machine Feedback

Timon Ziegenbein, Gabriella Skitalinskaya, Alireza Bayat Makou, Henning Wachsmuth


Abstract
Ensuring that online discussions are civil and productive is a major challenge for social media platforms. Such platforms usually rely both on users and on automated detection tools to flag inappropriate arguments of other users, which moderators then review. However, this kind of post-hoc moderation is expensive and time-consuming, and moderators are often overwhelmed by the amount and severity of flagged content. Instead, a promising alternative is to prevent negative behavior during content creation. This paper studies how inappropriate language in arguments can be computationally mitigated. We propose a reinforcement learning-based rewriting approach that balances content preservation and appropriateness based on existing classifiers, prompting an instruction-finetuned large language model (LLM) as our initial policy. Unlike related style transfer tasks, rewriting inappropriate arguments allows deleting and adding content permanently. It is therefore tackled on document level rather than sentence level. We evaluate different weighting schemes for the reward function in both absolute and relative human assessment studies. Systematic experiments on non-parallel data provide evidence that our approach can mitigate the inappropriateness of arguments while largely preserving their content. It significantly outperforms competitive baselines, including few-shot learning, prompting, and humans.
Anthology ID:
2024.acl-long.244
Volume:
Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
Month:
August
Year:
2024
Address:
Bangkok, Thailand
Editors:
Lun-Wei Ku, Andre Martins, Vivek Srikumar
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
4455–4476
Language:
URL:
https://aclanthology.org/2024.acl-long.244
DOI:
10.18653/v1/2024.acl-long.244
Bibkey:
Cite (ACL):
Timon Ziegenbein, Gabriella Skitalinskaya, Alireza Bayat Makou, and Henning Wachsmuth. 2024. LLM-based Rewriting of Inappropriate Argumentation using Reinforcement Learning from Machine Feedback. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 4455–4476, Bangkok, Thailand. Association for Computational Linguistics.
Cite (Informal):
LLM-based Rewriting of Inappropriate Argumentation using Reinforcement Learning from Machine Feedback (Ziegenbein et al., ACL 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.acl-long.244.pdf