Built independently by an author, for readers. Read the story and support ChapterPal
ChapterPal Logo
Log inSign up

keyword

paragraph-level detectors

Paragraph-level detectors are natural language processing and machine learning classification systems designed to analyze and evaluate text at the granularity of individual paragraphs rather than assessing an entire document as a single unit or evaluating isolated words and sentences. By operating at this intermediate scale, these systems capture enough linguistic and contextual structure to identify specific properties of a passage, such as whether it is human-written, machine-generated, or altered. This targeted approach enables the identification and localization of specific modified or synthetic sections within larger mixed documents, offering more precise attribution than document-wide models while maintaining richer contextual information than token-level or sentence-level methods.

1 item

Cross-Domain Detection of GPT-2-Generated Technical Text

Cross-Domain Detection of GPT-2-Generated Technical Text

Juan Diego Rodriguez, Todd Hay, David Gros, Zain Shamsi, Ravi Srinivasan

OrganizationsEn SoluciónUniversity of California, DavisUniversity of Texas at Austin

Why you should read this

Demonstrates that machine-generated technical text detectors can successfully transfer across distinct scientific domains with only a few hundred labeled examples, enabling effective identification of synthetic content and paragraph tampering in full-length research papers.

Machine-generated text presents a potential threat not only to the public sphere, but also to the scientific enterprise, whereby genuine research is undermined by convincing, synthetic text. In this paper we examine the problem of detecting GPT-2-generated technical research text. We first consider the realistic scenario where the defender does not have full information about the adversary's text generation pipeline, but is able to label small amounts of in-domain genuine and synthetic text in order to adapt to the target distribution. Even in the extreme scenario of adapting a physics-domain detector to a biomedical detector, we find that only a few hundred labels are sufficient for good performance. Finally, we show that paragraph-level detectors can be used to detect the tampering of full-length documents under a variety of threat models.

Added

2026-09-26