@article{insideyouaremanywolvesusingcognitive, title = {Inside you are many wolves: Using cognitive models to interpret value trade-offs in LLMs}, author = {Sonia K. Murthy and Rosie Zhao and Jennifer Hu and Sham Kakade and Markus Wulfmeier and Peng Qian and Tomer Ullman}, year = {2025}, eprint = {2506.20666}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2506.20666v1}, }