arXiv：cs.CL· Nudrat Habib, Tosin Adewumi, Sana Sabah Al-Azzawi, Marcus Liwicki, Elisa Barney·· 4 小时前AI 评分24
零样本作者归属的作者表示策略：LLM 与嵌入向量方法对比研究
Author Representation Strategies for Zero-Shot Authorship Attribution: A Comparative Study of LLM-Based and Embedding-Based Approaches
AI 导读
研究对比了零样本作者归属（AA）中不同作者表示策略的效果，包括仅标签提示、代表性写作样本、LLM 生成描述和风格嵌入向量（LISA）。结果显示仅标签提示无效，引入作者特定表示可稳定提升归属性能，其中两阶段 LISA 嵌入框架整体表现最强，LLM 生成风格描述则以更紧凑的表示换取部分性能损失。研究还指出当前开源 LLM 在缺乏更有效表示学习时仍不足以实现稳健的作者归属。
正文
Abstract:Authorship Attribution (AA) requires capturing fine-grained stylistic characteristics, making it particularly challenging in zero-shot (ZS) settings where no task-specific supervision is available. In this work, we investigate the effect of author representations on ZS AA by evaluating a label-only prompting baseline together with three author representation strategies: representative writing samples, LLM-generated descriptions, and style embeddings (LISA). The first three approaches perform attribution using LLM prompting, while the embedding-based approach uses style embeddings with cosine similarity. We investigate the influence of prompt design and propose a two-stage embedding-based attribution framework that combines candidate space reduction with embedding-dimension selection. The results show that label-only ZS AA is ineffective, while incorporating author-specific representations consistently improves attribution performance. Among the evaluated approaches, the proposed two-stage LISA framework achieves the strongest overall performance, whereas LLM-generated style descriptions provide a substantially more compact representation of author style at the cost of some attribution performance. These findings demonstrate the importance of author representation in ZS AA, while indicating that current open-source LLMs remain insufficient for robust attribution without more effective representation learning.
| Subjects: | Computation and Language (cs.CL) |
| Cite as: | arXiv:2610.03531 [cs.CL] |
| (or arXiv:2610.03531v1 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2610.03531 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Nudrat Habib [view email]
[v1]
Fri, 2 Oct 2026 16:16:47 UTC (363 KB)
来源：arXiv：cs.CL · arxiv.org