@article{traininglanguagemodelstoexplaintheirownc, title = {Training Language Models to Explain Their Own Computations}, author = {Belinda Z. Li and Zifan Carl Guo and Vincent Huang and Jacob Steinhardt and Jacob Andreas}, year = {2025}, eprint = {2511.08579}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2511.08579}, }