← Back to all news
arXiv Computation and Language By Rajesh Kumar, Nabeel Siddiqui, Alexander Fuchsberger

Detecting GPT-Assisted Writing Using Interpretable Stylometric Features

Read the original on arXiv Computation and Language →

The paper investigates whether stylometric features extracted only from text can distinguish GPT‑assisted writing from independently authored student work. Using data from 90 participants who produced both types of text, eight machine learning classifiers were tested, with Random Forest achieving an ROC‑AUC of 0.87 and an F1‑score of 0.84 on a held‑out test set. SHAP analysis revealed that lexical and grammatical characteristics were the primary drivers of the predictions, indicating that transparent, text‑intrinsic features can effectively signal GPT assistance.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computation and Language.

Related stories

arXiv Computation and Language
Oct 5

Writerslogic at the CLEF 2026 SimpleText Track: Multi-Candidate LLM Simplification and Stacked Complexity Spotting

The Writerslogic team participated in the CLEF 2026 SimpleText shared task, tackling both text simplification (Task 1) and complexity spotting (Task 2). For simplification, they built a multi‑candidate pipeline with GPT‑4o‑mini, selecting the best candidate via a reference‑free heuristic, and their Claude Sonnet 4 submission achieved a SARI of 47.43 and BLEU of 14.21, ranking third overall on the Task 1 leaderboard. For complexity spotting, they fine‑tuned a DeBERTa‑v3‑large NLI model on 350 K labeled pairs, achieving a macro F1 of 0.8081 (0.8085 in an ensemble) on binary over‑generation identification and 0.804 accuracy on multi‑class error classification, placing them second among unique teams.

By David L. Condrey
llmsfine-tuningbenchmarkssafety
More like this →
arXiv Machine Learning
Oct 3

Sentence Specificity Scores for Collaborative Technical Documentation: A Domain-Transfer Study

The paper investigates how sentence‑specificity scores can guide the selection of revisions in collaborative technical documentation. It compares two predictors—SpeciTeller and a target‑adapted model by Ko et al.—across Wikipedia and three technical corpora, finding that the predictors rank sentences differently and that SpeciTeller can improve direction‑valid selection rates in certain datasets. The study also shows that filtering and token‑length adjustments alter but do not reconcile these ranking differences.

By Rocker D'Antonio, Thomas Benton Townsend, Dimitrios Michael Manias
llms
More like this →