Safety
Detoxifying Toxic Communication: A Design Science Approach to Responsible AI
arXiv:2609.00361v1 Announce Type: cross Abstract: Toxic language in digital workplaces such as pejoratives, sarcasm, condescension, and subtle incivility can erode trust, morale, and collaboration. Ex
arXiv:2609.00361v1 Announce Type: cross Abstract: Toxic language in digital workplaces such as pejoratives, sarcasm, condescension, and subtle incivility can erode trust, morale, and collaboration. Existing moderation tools primarily delete or block harmful messages, disrupting communication and offering no constructive resolution. This study adopts a Design Science Research approach to create a responsible AI artifact that detects and detoxifies toxic communication. The artifact integrates fine-tuned transformer-based classifiers (DistilBERT, DistilRoBERTa) with a generative detoxification model (mT0-XL-Detox-ORPO) that rewrites toxic text into semantically equivalent, non-offensive paraphrases. Technical evaluation demonstrates high accuracy in toxicity detection and strong semantic preservation in rewritten messages, supporting conversation continuity while reinforcing respectful discourse. The paper contributes design principles for responsible AI moderation that prioritize meaning preservation and fairness.
Related
- On-Policy Distillation for LLM Safety: A Routing Approach to Template-Robust Realignment
- Understanding and Mitigating Bias Inheritance in LLM-based Data Augmentation on Downstream Tasks
- Toward Responsible and Epistemically Grounded Multilingual LLMs for Computational Social Science and Humanities
Source: arXiv cs.CL | 2026-09-02