@article{noiseinjectionrevealshiddencapabilities, title = {Noise Injection Reveals Hidden Capabilities of Sandbagging Language Models}, author = {Cameron Tice and Philipp Alexander Kreer and Nathan Helm-Burger and Prithviraj Singh Shahani and Fedor Ryzhenkov and Jacob Haimes and Felix Hofstätter and Teun van der Weij}, year = {2024}, eprint = {2412.01784}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2412.01784v1}, }