ALMs：用于作者归属的作者语言模型
ALMs: Authorial Language Models for Authorship Attribution
AI总结：
本文提出作者语言模型（ALMs），通过计算候选作者语料微调的因果语言模型对存疑文档的困惑度来识别作者，在Blogs50和CCAT50数据集上表现优异，并在短文本上进行了消融测试。
摘要：
本文介绍了一种名为作者语言模型（ALMs）的作者归属方法，该方法通过计算候选作者写作语料微调的一组因果语言模型对存疑文档的困惑度，来识别最可能的作者。我们使用CCAT50数据集和Blogs50数据集，将ALMs与最先进的系统进行了基准测试。结果发现，ALMs在Blogs50上取得了83.6%的宏平均准确率，优于所有其他方法；在CCAT50上达到74.9%，与最佳方法表现相当。为评估ALMs在较短文本上的表现，我们还进行了文本消融测试。结果表明，要达到70%的宏平均准确率，ALMs在Blogs50上需要40个token，在CCAT50上需要400个token；而要达到60%，在Blogs50上需20个token，在CCAT50上需70个token。
英文摘要：
In this paper, we introduce an authorship attribution method called Authorial Language Models (ALMs) that involves identifying the most likely author of a questioned document based on the perplexity of the questioned document calculated for a set of causal language models fine-tuned on the writings of a set of candidate author. We benchmarked ALMs against state-of-art-systems using the CCAT50 dataset and the Blogs50 datasets. We find that ALMs achieves a macro-average accuracy score of 83.6% on Blogs50, outperforming all other methods, and 74.9% on CCAT50, matching the performance of the best method. To assess the performance of ALMs on shorter texts, we also conducted text ablation testing. We found that to reach a macro-average accuracy of 70%, ALMs needs 40 tokens on Blogs50 and 400 tokens on CCAT50, while to reach 60% ALMs requires 20 tokens on Blogs50 and 70 tokens on CCAT50.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
