On the Detectability of ChatGPT Content: Benchmarking, Methodology, and Evaluation through the Lens of Academic Writing

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Liu, Zeyan, Yao, Zijun, Li, Fengjun, Luo, Bo
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917615551643648
author Liu, Zeyan
Yao, Zijun
Li, Fengjun
Luo, Bo
author_facet Liu, Zeyan
Yao, Zijun
Li, Fengjun
Luo, Bo
contents With ChatGPT under the spotlight, utilizing large language models (LLMs) to assist academic writing has drawn a significant amount of debate in the community. In this paper, we aim to present a comprehensive study of the detectability of ChatGPT-generated content within the academic literature, particularly focusing on the abstracts of scientific papers, to offer holistic support for the future development of LLM applications and policies in academia. Specifically, we first present GPABench2, a benchmarking dataset of over 2.8 million comparative samples of human-written, GPT-written, GPT-completed, and GPT-polished abstracts of scientific writing in computer science, physics, and humanities and social sciences. Second, we explore the methodology for detecting ChatGPT content. We start by examining the unsatisfactory performance of existing ChatGPT detecting tools and the challenges faced by human evaluators (including more than 240 researchers or students). We then test the hand-crafted linguistic features models as a baseline and develop a deep neural framework named CheckGPT to better capture the subtle and deep semantic and linguistic patterns in ChatGPT written literature. Last, we conduct comprehensive experiments to validate the proposed CheckGPT framework in each benchmarking task over different disciplines. To evaluate the detectability of ChatGPT content, we conduct extensive experiments on the transferability, prompt engineering, and robustness of CheckGPT.
format Preprint
id arxiv_https___arxiv_org_abs_2306_05524
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle On the Detectability of ChatGPT Content: Benchmarking, Methodology, and Evaluation through the Lens of Academic Writing
Liu, Zeyan
Yao, Zijun
Li, Fengjun
Luo, Bo
Computation and Language
Cryptography and Security
Machine Learning
With ChatGPT under the spotlight, utilizing large language models (LLMs) to assist academic writing has drawn a significant amount of debate in the community. In this paper, we aim to present a comprehensive study of the detectability of ChatGPT-generated content within the academic literature, particularly focusing on the abstracts of scientific papers, to offer holistic support for the future development of LLM applications and policies in academia. Specifically, we first present GPABench2, a benchmarking dataset of over 2.8 million comparative samples of human-written, GPT-written, GPT-completed, and GPT-polished abstracts of scientific writing in computer science, physics, and humanities and social sciences. Second, we explore the methodology for detecting ChatGPT content. We start by examining the unsatisfactory performance of existing ChatGPT detecting tools and the challenges faced by human evaluators (including more than 240 researchers or students). We then test the hand-crafted linguistic features models as a baseline and develop a deep neural framework named CheckGPT to better capture the subtle and deep semantic and linguistic patterns in ChatGPT written literature. Last, we conduct comprehensive experiments to validate the proposed CheckGPT framework in each benchmarking task over different disciplines. To evaluate the detectability of ChatGPT content, we conduct extensive experiments on the transferability, prompt engineering, and robustness of CheckGPT.
title On the Detectability of ChatGPT Content: Benchmarking, Methodology, and Evaluation through the Lens of Academic Writing
topic Computation and Language
Cryptography and Security
Machine Learning
url https://arxiv.org/abs/2306.05524