@article{learningselfinterpretationfrominterpreta, title = {Learning Self-Interpretation from Interpretability Artifacts: Training Lightweight Adapters on Vector-Label Pairs}, author = {Keenan Pepper and Alex McKenzie and Florin Pop and Stijn Servaes and Martin Leitgab and Mike Vaiana and Judd Rosenblatt and Michael S. A. Graziano and Diogo de Lucena}, year = {2026}, eprint = {2602.10352}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2602.10352}, }