@article{polarityawareprobingforquantifyinglatent, title = {Polarity-Aware Probing for Quantifying Latent Alignment in Language Models}, author = {Sabrina Sadiekh and Elena Ericheva and Chirag Agarwal}, year = {2025}, eprint = {2511.21737}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2511.21737}, }