Papilusion at DAGPap24: Paper or Illusion? Detecting AI-generated Scientific Papers

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Andreev, Nikita, Shirnin, Alexander, Mikhailov, Vladislav, Artemova, Ekaterina
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866917737297608704
author Andreev, Nikita
Shirnin, Alexander
Mikhailov, Vladislav
Artemova, Ekaterina
author_facet Andreev, Nikita
Shirnin, Alexander
Mikhailov, Vladislav
Artemova, Ekaterina
contents This paper presents Papilusion, an AI-generated scientific text detector developed within the DAGPap24 shared task on detecting automatically generated scientific papers. We propose an ensemble-based approach and conduct ablation studies to analyze the effect of the detector configurations on the performance. Papilusion is ranked 6th on the leaderboard, and we improve our performance after the competition ended, achieving 99.46 (+9.63) of the F1-score on the official test set.
format Preprint
id arxiv_https___arxiv_org_abs_2407_17629
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Papilusion at DAGPap24: Paper or Illusion? Detecting AI-generated Scientific Papers
Andreev, Nikita
Shirnin, Alexander
Mikhailov, Vladislav
Artemova, Ekaterina
Computation and Language
This paper presents Papilusion, an AI-generated scientific text detector developed within the DAGPap24 shared task on detecting automatically generated scientific papers. We propose an ensemble-based approach and conduct ablation studies to analyze the effect of the detector configurations on the performance. Papilusion is ranked 6th on the leaderboard, and we improve our performance after the competition ended, achieving 99.46 (+9.63) of the F1-score on the official test set.
title Papilusion at DAGPap24: Paper or Illusion? Detecting AI-generated Scientific Papers
topic Computation and Language
url https://arxiv.org/abs/2407.17629