SubmissionNumber#=%=#155
FinalPaperTitle#=%=#SemEval Task 8: A Comparison of Traditional and Neural Models for Detecting Machine Authored Text
ShortPaperTitle#=%=#
NumberOfPages#=%=#6
CopyrightSigned#=%=#Shrirang Rajendra Mhalgi
JobTitle#==#
Organization#==#Indiana University, 107 S Indiana Ave, Bloomington, IN 47405
Abstract#==#Since Large Language Models have reached a stage where it is becoming more and more difficult to distinguish between human and machine written text, there is an increasing need for automated systems to distinguish between them. As part of SemEval Task 8, Subtask A: Binary Human-Written vs. Machine-Generated Text Classification, we explore a variety of machine learning classifiers, from traditional statistical methods, such as Naïve Bayes and Decision Trees, to fine-tuned transformer models, such
as RoBERTa and ALBERT. Our findings show that using a fine-tuned RoBERTa model with optimized
hyperparameters yields the best accuracy. However, the improvement does not translate to the test set because of the differences in distribution in the development and test sets.
Author{1}{Firstname}#=%=#Srikar Kashyap
Author{1}{Lastname}#=%=#Pulipaka
Author{1}{Username}#=%=#spulipa
Author{1}{Email}#=%=#spulipa@iu.edu
Author{1}{Affiliation}#=%=#Indiana University Bloomington
Author{2}{Firstname}#=%=#Shrirang Rajendra
Author{2}{Lastname}#=%=#Mhalgi
Author{2}{Username}#=%=#srmhalgi
Author{2}{Email}#=%=#srmhalgi@iu.edu
Author{2}{Affiliation}#=%=#Indiana University Bloomington
Author{3}{Firstname}#=%=#Joseph E.
Author{3}{Lastname}#=%=#Larson
Author{3}{Username}#=%=#jelarson
Author{3}{Email}#=%=#joelarso@iu.edu
Author{3}{Affiliation}#=%=#Indiana University
Author{4}{Firstname}#=%=#Sandra
Author{4}{Lastname}#=%=#Kübler
Author{4}{Username}#=%=#skuebler
Author{4}{Email}#=%=#skuebler@indiana.edu
Author{4}{Affiliation}#=%=#Indiana University

==========
èéáğö