AIpom at SemEval-2024 Task 8: Detecting AI-produced Outputs in M4

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Shirnin, Alexander, Andreev, Nikita, Mikhailov, Vladislav, Artemova, Ekaterina
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866911818447847424
author Shirnin, Alexander
Andreev, Nikita
Mikhailov, Vladislav
Artemova, Ekaterina
author_facet Shirnin, Alexander
Andreev, Nikita
Mikhailov, Vladislav
Artemova, Ekaterina
contents This paper describes AIpom, a system designed to detect a boundary between human-written and machine-generated text (SemEval-2024 Task 8, Subtask C: Human-Machine Mixed Text Detection). We propose a two-stage pipeline combining predictions from an instruction-tuned decoder-only model and encoder-only sequence taggers. AIpom is ranked second on the leaderboard while achieving a Mean Absolute Error of 15.94. Ablation studies confirm the benefits of pipelining encoder and decoder models, particularly in terms of improved performance.
format Preprint
id arxiv_https___arxiv_org_abs_2403_19354
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle AIpom at SemEval-2024 Task 8: Detecting AI-produced Outputs in M4
Shirnin, Alexander
Andreev, Nikita
Mikhailov, Vladislav
Artemova, Ekaterina
Computation and Language
This paper describes AIpom, a system designed to detect a boundary between human-written and machine-generated text (SemEval-2024 Task 8, Subtask C: Human-Machine Mixed Text Detection). We propose a two-stage pipeline combining predictions from an instruction-tuned decoder-only model and encoder-only sequence taggers. AIpom is ranked second on the leaderboard while achieving a Mean Absolute Error of 15.94. Ablation studies confirm the benefits of pipelining encoder and decoder models, particularly in terms of improved performance.
title AIpom at SemEval-2024 Task 8: Detecting AI-produced Outputs in M4
topic Computation and Language
url https://arxiv.org/abs/2403.19354