@article{redefiningexpertsinterpretabledecomposit, title = {Redefining Experts: Interpretable Decomposition of Language Models for Toxicity Mitigation}, author = {Zuhair Hasan Shaik and Abdullah Mazhar and Aseem Srivastava and Md Shad Akhtar}, year = {2025}, eprint = {2509.16660}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2509.16660}, }