Saved in:
Bibliographic Details
Main Authors: Gritsai, German, Voznyuk, Anastasia, Khabutdinov, Ildar, Grabovoy, Andrey
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2411.11736
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910703510618112
author Gritsai, German
Voznyuk, Anastasia
Khabutdinov, Ildar
Grabovoy, Andrey
author_facet Gritsai, German
Voznyuk, Anastasia
Khabutdinov, Ildar
Grabovoy, Andrey
contents The paper describes a system designed by Advacheck team to recognise machine-generated and human-written texts in the monolingual subtask of GenAI Detection Task 1 competition. Our developed system is a multi-task architecture with shared Transformer Encoder between several classification heads. One head is responsible for binary classification between human-written and machine-generated texts, while the other heads are auxiliary multiclass classifiers for texts of different domains from particular datasets. As multiclass heads were trained to distinguish the domains presented in the data, they provide a better understanding of the samples. This approach led us to achieve the first place in the official ranking with 83.07% macro F1-score on the test set and bypass the baseline by 10%. We further study obtained system through ablation, error and representation analyses, finding that multi-task learning outperforms single-task mode and simultaneous tasks form a cluster structure in embeddings space.
format Preprint
id arxiv_https___arxiv_org_abs_2411_11736
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Advacheck at GenAI Detection Task 1: AI Detection Powered by Domain-Aware Multi-Tasking
Gritsai, German
Voznyuk, Anastasia
Khabutdinov, Ildar
Grabovoy, Andrey
Computation and Language
The paper describes a system designed by Advacheck team to recognise machine-generated and human-written texts in the monolingual subtask of GenAI Detection Task 1 competition. Our developed system is a multi-task architecture with shared Transformer Encoder between several classification heads. One head is responsible for binary classification between human-written and machine-generated texts, while the other heads are auxiliary multiclass classifiers for texts of different domains from particular datasets. As multiclass heads were trained to distinguish the domains presented in the data, they provide a better understanding of the samples. This approach led us to achieve the first place in the official ranking with 83.07% macro F1-score on the test set and bypass the baseline by 10%. We further study obtained system through ablation, error and representation analyses, finding that multi-task learning outperforms single-task mode and simultaneous tasks form a cluster structure in embeddings space.
title Advacheck at GenAI Detection Task 1: AI Detection Powered by Domain-Aware Multi-Tasking
topic Computation and Language
url https://arxiv.org/abs/2411.11736