DART: An AIGT Detector using AMR of Rephrased Text

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Park, Hyeonchu, Kim, Byungjun, Kim, Bugeun
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909475584081920
author Park, Hyeonchu
Kim, Byungjun
Kim, Bugeun
author_facet Park, Hyeonchu
Kim, Byungjun
Kim, Bugeun
contents As large language models (LLMs) generate more human-like texts, concerns about the side effects of AI-generated texts (AIGT) have grown. So, researchers have developed methods for detecting AIGT. However, two challenges remain. First, the performance of detecting black-box LLMs is low because existing models focus on probabilistic features. Second, most AIGT detectors have been tested on a single-candidate setting, which assumes that we know the origin of an AIGT and which may deviate from the real-world scenario. To resolve these challenges, we propose DART, which consists of four steps: rephrasing, semantic parsing, scoring, and multiclass classification. We conducted three experiments to test the performance of DART. The experimental result shows that DART can discriminate multiple black-box LLMs without probabilistic features and the origin of AIGT.
format Preprint
id arxiv_https___arxiv_org_abs_2412_11517
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle DART: An AIGT Detector using AMR of Rephrased Text
Park, Hyeonchu
Kim, Byungjun
Kim, Bugeun
Computation and Language
Artificial Intelligence
As large language models (LLMs) generate more human-like texts, concerns about the side effects of AI-generated texts (AIGT) have grown. So, researchers have developed methods for detecting AIGT. However, two challenges remain. First, the performance of detecting black-box LLMs is low because existing models focus on probabilistic features. Second, most AIGT detectors have been tested on a single-candidate setting, which assumes that we know the origin of an AIGT and which may deviate from the real-world scenario. To resolve these challenges, we propose DART, which consists of four steps: rephrasing, semantic parsing, scoring, and multiclass classification. We conducted three experiments to test the performance of DART. The experimental result shows that DART can discriminate multiple black-box LLMs without probabilistic features and the origin of AIGT.
title DART: An AIGT Detector using AMR of Rephrased Text
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2412.11517