MAAT is a three-phase unlearning framework designed to address the structural skew in machine unlearning evaluation, particularly focusing on "Why-type" questions that probe causal and relational knowledge. The method operates exclusively on LoRA adapter weights, combining gradient-projected ascent, SVD rank-dimension pruning, task vector negation, and hybrid KL-hidden-state retain repair.
The MAAT framework establishes a new operating point on the forget-retain Pareto frontier. It achieves high forgetting and high retention on causal knowledge by:
1@article{yagnik2026maat,
2 title={MAAT: Multi-phase Adapter-Aware Targeted Unlearning},
3 author={Yagnik, Suryash and Gaur, Shubham and Thakur, Saksham and Jain, Vinija and Chadha, Aman and Das, Amitava},
4 journal={arXiv preprint arXiv:2605.30514},
5 year={2026}
6}
