International Science Editing

International Science Editing
Providers of Premier Scientific Editing Services
We speak your language
International Science Editing Portuguese website International Science Editing Japanese website International Science Editing Chinese website
  • Home
  • Services
    • Editing Services
      • Standard Editing
      • Premium Editing Service
      • Multiservice Package
    • Submission Support Services
      • Graphing
      • Custom Illustration
      • Figure Formatting
      • Journal Specific Formatting
      • Manuscript Review
      • Response to Reviewers
      • Multiservice Package
      • Cover Letter Writing
      • Lay Summary
    • Translation
    • Promote Your Research
  • Create Your Order
    • Editing
    • Submission Support Services
      • Manuscript Review Service
      • Figure Formatting
      • Custom Illustrations
      • Graphing
      • Video Abstracts and Video Bytes
      • Journal Specific Formatting
      • Multiservice Package
      • Response to Reviewers
      • Cover Letter Writing
      • Lay Summary
    • Translation
    • Promote Your Research
  • Payment
  • Writing Tips
    • Latest Posts
    • Manuscript Preparation
    • Journal Selection
    • Peer-Review
    • Publication Ethics
    • Research Promotion
    • Submitting an Article
    • Abstracts
    • Cover Letters
    • Request for Revision
  • Customer Service
    • FAQs
    • Feedback from our Clients
    • Approved Provider of Editing Services
    • Terms of Service
      • Security Policy
      • Privacy Policy
      • Cookie Policy
      • Disclaimer
  • 访问我们的中文网页
  • About Us
    • Our Team
    • How Our Service Works
    • Publishers
    • Approved Provider of Editing Services
  • Contact Us
You are here: Home / Archives / When ChatGPT gets it wrong

June 6, 2023 by Lisa Clancy

When ChatGPT gets it wrong

ChatGPT’s capabilities are irrefutable. However, when asked to edit the language of scientific papers, it can make mistakes. Crucially, ChatGPT best guesses the next word; it cannot deduce the author’s intended meaning in the same way an experienced subject-matter expert can, and it cannot leave comments asking for clarification as a human editor would do. In this blog, we present the mistakes we found when we tested ChatGPT against our human editors.

ChatGPT can change the author’s intended meaning.table image 1

In the example above, ChatGPT changed “poor activity” to “limited mobility,” potentially changing the author’s meaning. Our editor was unsure of the expression “poor activity” in the context presented here and therefore added a comment asking the author to explain their intended meaning. This illustrates one of the key downsides of ChatGPT – it cannot engage in a back-and-forth with the author to ensure their intended meaning is conveyed; it presents its best guess.

table image 2

In the example above, ChatGPT excluded the text “and the inferior vena cava,” potentially changing the author’s meaning.

table image 3

In the example above, ChatGPT changed the text “after the second round of hospital consultation” to “after consulting the hospital for a second opinion,” slightly changing the author’s meaning. The difference here is subtle but potentially important. The unedited version, i.e., “after the second round of hospital consultation,” implies that the second round of consultation had been planned as part of the methodology; ChatGPT’s edit suggests that the “second opinion” was requested only after receiving the first consultation.

table image 4

In the example above, ChatGPT missed the author’s intended meaning, i.e., a description of the criteria of the study. Instead, ChatGPT presented the information as a general truth.

table image 4

In the example above, the authors were trying to give an overview of the MTT assay. ChatGPT’s edit, however, made it appear that the authors had used the MTT assay to measure cell survival and growth in the study, which is incorrect. ChatGPT’s editing of the last sentence, “This process is not available in dead cells,” is also poorly phrased.

table image 5

In the example above, the authors were trying to present a description of previous works completed. ChatGPT misinterpreted this and presented the information as if it were a description of the aims of the study. In addition, our editor left a comment for the authors suggesting they add a citation for the mentioned works.

ChatGPT can add words inappropriately.

table image 6

In the example above, ChatGPT inappropriately added the word “initially.”

table image 7

In the example above, ChatGPT inappropriately added the word “however,” thus implying that an increase in antenna size is a downside of the approach, which was not the author’s intended meaning.

table image 8

In the example above, ChatGPT inappropriately added the word “initially.” In addition, “After unearthing 1-2 cm of the broad bean seedlings …” is poorly phrased, and ChatGPT failed to change “Aphis” to “aphids.”

table image 9

In the example above, ChatGPT added a description of why the methodology, “qPCR screening,” was used, resulting in some redundancy.

ChatGPT can make poor word choices.

table image 10

In the example above, ChatGPT inappropriately changed “allogenic” to “exogenous,” possibly because allogenic was spelled wrong in the original, unedited version.

table image 11

ChatGPT changed “single use” to “individually” in the example above, making the red text nonsensical.

table image 12

In the example above, our editor improved the clarity of the text by changing “intercept” to “trap.” Also, GPT failed to correct the typo, i.e., change “NF elements” to “NM elements.” Our editor knew to correct this, as they had access to the full paper; ChatGPT has a word limit.
table image 13

In the example above, ChatGPT failed to change the inappropriate use of the word “construction” and failed to improve the grammar of the phrase “under challenging habitats.”

ChatGPT can fail to improve clarity.

table image 14

In the example above, our editor improved the overall flow and clarity of the text much better than ChatGPT. In addition, ChatGPT failed to use the numeral for units of measurement, e.g., “one year” should be presented as “1 year.”

table image 15

In the example above, our editor improved the clarity of the text better than ChatGPT.

table image 16

In the example above, our editor makes it very clear what the authors did. By retaining the awkward phrasing “comparative experiment,” ChatGPT failed to improve the clarity of the text.

ChatGPT can use the wrong tense.

table image 17

In this example, ChatGPT changed the tense to the present tense. Results are traditionally presented in the past tense.

ChatGPT can use the wrong subject-verb agreement.

table image 18

In the example above, ChatGPT used the plural “were” with the singular “1.8 grams of double-distilled water,” which is incorrect.

table image 18

In the example above, ChatGPT used the singular “undergoes” with the plural “viscera,” which is incorrect.

ChatGPT can delete information.

table image 19

In the example above, ChatGPT deleted information, i.e., “softens berries.”

ChatGPT can inappropriately rearrange the text.

table image 20

In the example above, ChatGPT rearranged the text to imply that the downside of the proposed method is that the profile of the antenna is increased. This does not convey the author’s intended meaning.

Other examples of poor grammar by ChatGPT

table image 21

In the example above, “… has unclear toxicity and mechanism” is poorly phrased.

table image 22
In the example above, “… operates on a similar mechanism” is awkward phrasing.

table image 23

In the example above, ChatGPT failed to adhere to a typical journal formatting rule which specifies that Latin names should be written out in full if they begin a sentence.

table image 24

A compound adjective in which the first word ends in ‘ly’ should not contain a hyphen. ChatGPT failed to correct this.

ChatGPT can do odd things with references.

table image 24

In the example above, ChatGPT changed the in-text citations from numbers to text; however, these were the wrong references.

table image 25

In the example above, ChatGPT added a reference that was not in the original, unedited version.

table image 26

In the example above, ChatGPT removed the references “Lo et al., 2010” and “Tei et al., 2017,” possibly because the opening parenthesis was in the font SimSun in the original, unedited version.

table image 27

In the example above, ChatGPT changed the numbered in-text citation to “Author, 2021.” This happened several times during our testing of ChatGPT.

table image 28

In the example above, ChatGPT changed the in-text citation from “Linlin et al.” to “Chen et al.” It is understandable why ChatGPT may have done this; however, it is not clear what the authors meant here. Our editor left a comment asking the authors to clarify.

table image 29

ChatGPT changed “Lffler” to the more common spelling Löffler; however, this was not correct in this case.

In conclusion …

Large language models like ChatGPT will undoubtedly continue to improve. For now, however, human editors remain the best way to get your papers publication-ready.

Filed Under: Archives, Latest Posts, Manuscript Preparation, Publication Ethics Tagged With: ChatGPT, grammar mistakes, human editor, language editing, large language model, publish paper using ChatGPT, scientific papers

Chinese website

访问我们的中文网页

我们会将您的手稿交给与您所在研究领域相匹配的英语母语学术编辑进行润色,他们将修正拼写,语法,标点和句法错误。 编辑还将改进句子结构,并确保使用符合科学论文写作的专业用语。

Trusted by Publishers and Societies

  • Society of Child Development
  • SAE International
  • American Society of Hematology
  • American Association for Nutrition
  • American Meteorological Society
  • American Society for Microbology
  • American Association for Mechanical Engineering
  • American Society of Civil Engineers
  • American Psychological Association
  • Association for Computing Machinery
  • American Academy of Otolaryngology Head and Neck Surgery
  • American Society of Cancer Research

Price Calculator

The word copyright is highlighted in a dictionary

Can images from the Internet or a Chinese-language journal be used for publication in a different journal?

Yes, you can re-use images from the Internet and Chinese-language journals if you have obtained the necessary copyright permissions and you cite the original source (in the figure legend). Journals will not accept re-used images for which you have not obtained the necessary permissions. Check the copyright of the image If you want to re-use […]

Currency converter

European Office

Tel: +353 61 472818
International Science Editing
Compuscript Ltd,
Shannon Industrial Estate West,
Shannon, Republic of Ireland.

Chinese Office

Tel: 0512-67621565, 0512-87661520
International Science Editing
Room 2013, Locca Tower,
8th Jiarui Road,
Suzhou Industrial Park, Suzhou,
Jiangsu Province, China.
访问我们的中文网页

North American Office

Tel: 717-668-9325
International Science Editing
2930 Legacy Lane,
York,
Pennsylvania, 17402,
U.S.A.

Copyright © 2025 · INTERNATIONAL SCIENCE EDITING · ALL RIGHTS RESERVED

Real Time Web Analytics
We’ve updated our Privacy Policy and Cookie Policy. These updates address new privacy regulations in Europe and apply to everyone who uses International Science Editing including clients, authors and partners.
Click on Settings to view the list of cookies, the different category headings, and/or change the default settings. Please click on “Accept” to continue to use International Science Editing Accept
Privacy & Cookies Policy

Privacy Overview

This website uses cookies to improve your experience while you navigate through the website. Out of these cookies, the cookies that are categorized as necessary are stored on your browser as they are essential for the working of basic functionalities of the website. We also use third-party cookies that help us analyze and understand how you use this website. These cookies will be stored in your browser only with your consent. You also have the option to opt-out of these cookies. But opting out of some of these cookies may have an effect on your browsing experience.
Necessary
Always Enabled

These cookies do not store any directly identifiable information. However, they are necessary for the Service to function. They are usually only set in response to actions made by you which amount to a request for services, such as setting your privacy preferences, logging in, or filling in forms. You can set your browser to block or alert you about these cookies, but without these cookies, some or all of the services you have asked for may not work properly.

Analytics

Analytical cookies are used to understand how visitors interact with the website. These cookies help provide information on metrics the number of visitors, bounce rate, traffic source, etc.

Uncategorized

Undefined cookies are those that are being analyzed and have not been classified into a category as yet.

Performance

These are analytics and research cookies that allow us to count visits and measure traffic, so we can measure and improve the performance of our Services. They also help us to know which pages are the most and least popular and see how visitors move around the site(s) or application(s). This helps us to improve the way our Services work and improve user experience. You can set your browser to block or alert you about these cookies. Blocking these cookies will not affect the service provided to you.

Preferences

Preference cookies are used to store user preferences to provide content that is customized and convenient for the users, like the language of the website or the location of the visitor.

Targeting

These files, or code may be included, either directly or from our advertising partners, on our website, in our emails, or mobile applications to record how you interact with us, to help us better analyse and improve our services to you, and will use this information to make the website, and, any advertising displayed to you more relevant to your interests. You can set your browser to block or alert you about these cookies. Blocking these cookies will not affect the service provided to you but will limit the targeted advertising that you will see or limit our ability to tailor the website experience to your needs.

Save & Accept