arXiv cs.CL· Yassir El Attar, Esra D\"onmez, Maximilian Maurer, Agnieszka Falenska·· 11 小时前AI 评分35
研究：284 个语言特征在 30 个 LLM 与 10 类文本域上的 AI 生成文本检测效果
A Systematic Analysis of Linguistic Features in AI-Generated English Text Detection Across Domains and Models
AI 导读
一项大规模实证研究评估了 284 个可解释语言特征在 30 个 LLM、10 类文本域下的跨模型与跨域泛化表现，发现仅靠语言特征的分类器即可可靠区分 AI 生成文本与人类写作。但此前提出的多数指标强烈依赖语境，只有词汇丰富度指标在跨模型家族和文本域时保持稳健。
正文 · 原文
Abstract:Interpretable linguistic features offer a promising approach for explaining why a given text appears machine-generated, particularly for non-expert users. However, existing findings on which features reliably indicate LLMgenerated text remain fragmented across feature sets, models, and text domains. To address this gap, we conduct a large-scale empirical study assessing the robustness of linguistic signals for characterizing AI-generated text. Our analysis covers 284 interpretable linguistic features across outputs from 30 LLMs and 10 text domains under cross-model and cross-domain generalization settings. We show that classifiers based solely on linguistic features can reliably distinguish AI-generated from human-written text. However, many previously proposed indicators prove strongly context-dependent, with the exception of measures of lexical richness, which remain robust signals across model families and text domains. These results demonstrate which linguistic signals generalize across contexts and provide a foundation for more reliable, interpretable analyses of AI-generated language.
| Subjects: | Computation and Language (cs.CL); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2606.04177 [cs.CL] |
| (or arXiv:2606.04177v2 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2606.04177 arXiv-issued DOI via DataCite |
Submission history
From: Esra Dönmez [view email]
[v1]
Tue, 2 Jun 2026 19:46:22 UTC (8,530 KB)
[v2]
Sat, 31 Oct 2026 19:40:06 UTC (1,160 KB)
来源：arXiv cs.CL · arxiv.org