@article{benchmarkingmentalstaterepresentationsin, title = {Brittle Minds, Fixable Activations: Understanding Belief Representations in Language Models}, author = {Matteo Bortoletto and Constantin Ruhdorfer and Lei Shi and Andreas Bulling}, year = {2024}, eprint = {2406.17513}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2406.17513v3}, }