← Back to archive day

Beyond the Final Actor: Modeling the Dual Roles of Creator and Editor for Fine-Grained LLM-Generated Text Detection

Yang Li, Qiang Sheng, Zhengjia Wang, Yehan Yang, Danding Wang, Juan Cao

36

Recommendation Score

breakthrough🟡 IntermediateNLPLLM ReasoningTheoryUseful for both

Research context

Primary field

NLP

Language understanding, generation, extraction, and evaluation.

Topics

LLM Reasoning

Paper type

Theory

Best for

Useful for both

arXiv categories

cs.CLcs.CL

Why It Matters

This is the first system that can tell if text was written by a human, edited by an LLM, written by an LLM, or polished by a human—critical for content moderation and legal compliance. You can no longer rely on simple 'AI or human' detectors; this gives you real nuance.

Abstract

The misuse of large language models (LLMs) requires precise detection of synthetic text. Existing works mainly follow binary or ternary classification settings, which can only distinguish pure human/LLM text or collaborative text at best. This remains insufficient for the nuanced regulation, as the LLM-polished human text and humanized LLM text often trigger different policy consequences. In this paper, we explore fine-grained LLM-generated text detection under a rigorous four-class setting. To handle such complexities, we propose RACE (Rhetorical Analysis for Creator-Editor Modeling), a fine-grained detection method that characterizes the distinct signatures of creator and editor. Specifically, RACE utilizes Rhetorical Structure Theory to construct a logic graph for the creator's foundation while extracting Elementary Discourse Unit-level features for the editor's style. Experiments show that RACE outperforms 12 baselines in identifying fine-grained types with low false alarms, offering a policy-aligned solution for LLM regulation.

Published April 6, 2026
© 2026 A2A.pub — AI to Action. From papers to practice, daily.
Summaries are AI-assistedPrivacyTerms