@inproceedings{inproceedings7bd7f088, title = {Extracting and understanding the superficial knowledge in alignment}, author = {Chen, Runjin and Perin, Gabriel Jacob and Chen, Xuxi and Chen, Xilun and Han, Yan and Hirata, Nina Sumiko Tomita and Hong, Junyuan and Kailkhura, Bhavya}, year = {2025}, doi = {10.18653/v1/2025.naacl-long.168}, publisher = {ACL}, booktitle = {Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies} }