arXiv cs.CL· Gonzalo Freijedo Aduna (IJN), Charles Yaiche (CRIStAL), Patrick Bas (CRIStAL), Alda Mari (IJN)·· 11 小时前AI 评分31
SAGE：利用主观性语言特征检测 AI 生成同行评审的框架
SAGE (Subjectivity-Aware Generation Estimator): A Linguistic Framework for AI-Generated Review Detection *
AI 导读
研究者提出 SAGE 框架，从语义层的评价性语言与情态、语用层的言语行为两个层面捕捉主观性，仅用这些语言特征训练的轻量分类器即达到 0.9566 的 AUROC。将其输出与 SOTA 检测器 Sem-Detect 结合后，在 APRDB 基准上 1% FPR 下的 TPR 从 0.874 提升至 0.985，超过当前最优水平。代码与模型已在 GitHub 和 Hugging Face 公开。
正文 · 原文
Abstract:We propose a simple, linguistically motivated approach to detecting AI-generated peer reviews based on the inherently human trait of subjectivity. We capture subjectivity at two levels: the semantic level of evaluative language and modality and the pragmatic level of speech acts. Using features derived from speech act annotations and model-predicted subjectivity scores, we train a lightweight classifier that achieves an AUROC of 0.9566 with only these linguistic features. Combining its output with the state-of-the-art detector Sem-Detect raises the TPR at 1% FPR of Sem-Detect on the APRDB benchmark from 0.874 to 0.985, outperforming the current state of the art. Our results show that linguistic features of subjectivity provide an explainable source of information for detecting AI-generated peer reviews and can be readily integrated into existing detection methods. The code and models are publicly available on GitHub (this https URL\_ text\_detection\_hub) and Hugging Face (this https URL), respectively.
| Subjects: | Computation and Language (cs.CL) |
| Cite as: | arXiv:2611.03060 [cs.CL] |
| (or arXiv:2611.03060v1 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2611.03060 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Patrick Bas [view email] [via CCSD proxy]
[v1]
Mon, 2 Nov 2026 12:50:19 UTC (468 KB)
来源：arXiv cs.CL · arxiv.org