SubmissionNumber#=%=#254
FinalPaperTitle#=%=#AIpom at SemEval-2024 Task 8: Detecting AI-produced Outputs in M4
ShortPaperTitle#=%=#
NumberOfPages#=%=#6
CopyrightSigned#=%=#EArt
JobTitle#==#
Organization#==#
Abstract#==#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.
Author{1}{Firstname}#=%=#Alexander
Author{1}{Lastname}#=%=#Shirnin
Author{1}{Username}#=%=#manoftheyear
Author{1}{Email}#=%=#alexamailwork@gmail.com
Author{1}{Affiliation}#=%=#HSE University
Author{2}{Firstname}#=%=#Nikita
Author{2}{Lastname}#=%=#Andreev
Author{2}{Username}#=%=#nikich28
Author{2}{Email}#=%=#nikita01n01@gmail.com
Author{2}{Affiliation}#=%=#Skoltech
Author{3}{Firstname}#=%=#Vladislav
Author{3}{Lastname}#=%=#Mikhailov
Author{3}{Username}#=%=#vmkhlv
Author{3}{Email}#=%=#vmikhailovhse@gmail.com
Author{3}{Affiliation}#=%=#University of Oslo
Author{4}{Firstname}#=%=#Ekaterina
Author{4}{Lastname}#=%=#Artemova
Author{4}{Username}#=%=#artemovae
Author{4}{Email}#=%=#ekaterina.l.artemova@gmail.com
Author{4}{Affiliation}#=%=#Toloka.AI

==========
èéáğö