语言模型难以真实模拟历史风格，需用时期文本预训练才可信。
Can Language Models Represent the Past without Anachronism?
- 用时代文本微调模型可骗过自动评测
- 人类仍能识别出伪造的历史文本
- 研究历史视角需在时期文本上预训练
在使用语言模型模拟历史之前，必须理解其产生时代错乱的风险。我们发现，仅用时代文风示例提示当代模型，无法生成符合时代风格的输出。微调后生成内容在自动化评判中表现可信，但人类评估者仍可区分模型输出与真实历史文本。初步结论是，为可靠模拟历史视角进行社会研究，可能需要在时期文本上进行预训练。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。