用于文体分析与可解释作者归属的潜在空间解释方法
Latent Space Interpretation for Stylistic Analysis and Explainable Authorship Attribution
AI总结：
针对现有作者归属方法潜在空间不可解释的问题，提出通过识别潜在空间代表点并利用LLM生成风格自然语言描述的解释方法，实现了最优预测一致性，且能将人类完成作者归属任务的准确率平均提升约20%。
摘要：
当前最先进的作者归属方法在不可解释的潜在空间中学习文本的作者身份表示，阻碍了其在实际场景中的应用。本文提出一种新方法，通过识别潜在空间中的代表性点，并利用大语言模型（LLM）为每个点的写作风格生成有信息量的自然语言描述，来解释这些学到的嵌入向量。我们评估了可解释空间与潜在空间的对齐程度，发现与其他基线相比，该方法实现了最优的预测一致性。此外，我们开展了人工评估以检验风格描述的质量，验证了其作为潜在空间解释的实用性。最后，我们探究了在具有挑战性的作者归属（AA）任务中，借助本系统的解释能否提升人类表现，结果显示准确率平均提升约20%。
英文摘要：
Recent state-of-the-art authorship attribution methods learn authorship representations of texts in a latent, non-interpretable space, hindering their usability in real-world applications. Our work proposes a novel approach to interpreting these learned embeddings by identifying representative points in the latent space and utilizing LLMs to generate informative natural language descriptions of the writing style of each point. We evaluate the alignment of our interpretable space with the latent one and find that it achieves the best prediction agreement compared to other baselines. Additionally, we conduct a human evaluation to assess the quality of these style descriptions, validating their utility as explanations for the latent space. Finally, we investigate whether human performance on the challenging AA task improves when aided by our system's explanations, finding an average improvement of around +20% in accuracy.
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。
