Detecting LLM-assisted writing in scientific communication: Are we there yet?

Large Language Models (LLMs), exemplified by ChatGPT, have significantly reshaped text generation, particularly in the realm of writing assistance. While ethical considerations underscore the importance of transparently acknowledging LLM use, especially in scientific communication, genuine acknowled...

Full description

Saved in:
Bibliographic Details
Main Authors: Lazebnik Teddy, Rosenfeld Ariel
Format: Article
Language:English
Published: Sciendo 2024-07-01
Series:Journal of Data and Information Science
Subjects:
Online Access:https://doi.org/10.2478/jdis-2024-0020
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849317018586578944
author Lazebnik Teddy
Rosenfeld Ariel
author_facet Lazebnik Teddy
Rosenfeld Ariel
author_sort Lazebnik Teddy
collection DOAJ
description Large Language Models (LLMs), exemplified by ChatGPT, have significantly reshaped text generation, particularly in the realm of writing assistance. While ethical considerations underscore the importance of transparently acknowledging LLM use, especially in scientific communication, genuine acknowledgment remains infrequent. A potential avenue to encourage accurate acknowledging of LLM-assisted writing involves employing automated detectors. Our evaluation of four cutting-edge LLM-generated text detectors reveals their suboptimal performance compared to a simple ad-hoc detector designed to identify abrupt writing style changes around the time of LLM proliferation. We contend that the development of specialized detectors exclusively dedicated to LLM-assisted writing detection is necessary. Such detectors could play a crucial role in fostering more authentic recognition of LLM involvement in scientific communication, addressing the current challenges in acknowledgment practices.
format Article
id doaj-art-b7bf73064a1144bcb9b385dd0bed9033
institution Kabale University
issn 2543-683X
language English
publishDate 2024-07-01
publisher Sciendo
record_format Article
series Journal of Data and Information Science
spelling doaj-art-b7bf73064a1144bcb9b385dd0bed90332025-08-20T03:51:24ZengSciendoJournal of Data and Information Science2543-683X2024-07-019341310.2478/jdis-2024-0020Detecting LLM-assisted writing in scientific communication: Are we there yet?Lazebnik Teddy0Rosenfeld Ariel11Department of Mathematics, Ariel University, Ariel, Israel3Department of Information Science, Bar Ilan University, Ramat Gan, IsraelLarge Language Models (LLMs), exemplified by ChatGPT, have significantly reshaped text generation, particularly in the realm of writing assistance. While ethical considerations underscore the importance of transparently acknowledging LLM use, especially in scientific communication, genuine acknowledgment remains infrequent. A potential avenue to encourage accurate acknowledging of LLM-assisted writing involves employing automated detectors. Our evaluation of four cutting-edge LLM-generated text detectors reveals their suboptimal performance compared to a simple ad-hoc detector designed to identify abrupt writing style changes around the time of LLM proliferation. We contend that the development of specialized detectors exclusively dedicated to LLM-assisted writing detection is necessary. Such detectors could play a crucial role in fostering more authentic recognition of LLM involvement in scientific communication, addressing the current challenges in acknowledgment practices.https://doi.org/10.2478/jdis-2024-0020llm-assisted writingscientific communicationwriting style
spellingShingle Lazebnik Teddy
Rosenfeld Ariel
Detecting LLM-assisted writing in scientific communication: Are we there yet?
Journal of Data and Information Science
llm-assisted writing
scientific communication
writing style
title Detecting LLM-assisted writing in scientific communication: Are we there yet?
title_full Detecting LLM-assisted writing in scientific communication: Are we there yet?
title_fullStr Detecting LLM-assisted writing in scientific communication: Are we there yet?
title_full_unstemmed Detecting LLM-assisted writing in scientific communication: Are we there yet?
title_short Detecting LLM-assisted writing in scientific communication: Are we there yet?
title_sort detecting llm assisted writing in scientific communication are we there yet
topic llm-assisted writing
scientific communication
writing style
url https://doi.org/10.2478/jdis-2024-0020
work_keys_str_mv AT lazebnikteddy detectingllmassistedwritinginscientificcommunicationarewethereyet
AT rosenfeldariel detectingllmassistedwritinginscientificcommunicationarewethereyet