Paper analyzes linguistic features to detect AI-generated text

Arxiv CS.CL (NLP/language models)

The paper systematically analyzes which linguistic features reliably indicate LLM-generated text across domains and models. Interpretable features offer a promising approach for non-expert users to understand why a text appears machine-generated.

ai-detectionlinguistic-features

Arxiv CS.CL (NLP/language models)·Yassir El AttarEsra D\"onmezMaximilian MaurerAgnieszka Falenska

7 days ago