Before researchers can use language models to simulate the past, they need to understand the risk of anachronism. We find that prompting a contemporary model with examples of period prose does not produce output consistent with period style. Fine-tuning produces results that are stylistically convincing enough to fool an automated judge, but human evaluators can still distinguish fine-tuned model outputs from authentic historical text. We tentatively conclude that pretraining on period prose may be required in order to reliably simulate historical perspectives for social research.
@article{arxiv.2505.00030,
title = {Can Language Models Represent the Past without Anachronism?},
author = {Ted Underwood and Laura K. Nelson and Matthew Wilkens},
journal= {arXiv preprint arXiv:2505.00030},
year = {2025}
}