AI in the writing process

AI at the university

The TUD is open to the use of (text-generating) AI systems as of May 2024. Specific guidelines can be found on the University Executive Board's website.

The term "artificial intelligence" covers a broad field of research. In scientific writing, the focus is on large language models (LLM) such as ChatGPT. In common parlance, "AI" has become established, which is why we also use this term to refer to LLMs.

The implementation of AI systems in the writing process offers numerous advantages, but also harbors the potential for unreflected dependency. In order for AI to support learning, reading and writing processes profitably, a competent and critical approach to this technology is a basic prerequisite.

The TUD Writing Center is the point of contact for all questions relating to the use of AI in academic writing. We are also happy to provide individual advice. This service is aimed at both students and teaching staff.

Offers for teachers

Starting aid for writing didactics

In the brochure "Starthilfe Schreibdidaktik" (Jump-Start your Writing Didactics) published by the SZD, you will find a chapter on the use of AI applications in teaching and the evaluation of their use by students.

You can download the brochure "Starthilfe Schreibdidaktik" here.

Workshop series "AI tools and academic writing" (German language)

Both workshops for lecturers take place regularly once per semester. If you are interested in additional dates, please contact:

Workshop "AI tools and scientific writing I. Basics and Challenges" with Paulina Hösl; date tba, presence in the Fritz-Foerster-Bau, registration on OPAL
Workshop "AI tools and scientific writing II. Competencies in the writing process" with Paulina Hösl: Thursday, June 27, 9:30-13:00, presence in the Fritz-Foerster-Bau, registration until June 19 on OPAL

Offers for students (German language)

The AI workshops for students regularly take place once per semester. If you are interested in further dates and offers (e. g. workshops in English language), please sign up for our list of interested parties on Opal.

Topic focus "AI and scientific Writing" as part of the open writing room
25.06.2024 14:50-16:20, presence in Fritz-Foerster-Bau room 135, registration on OPAL
Workshop "AI-supported scientific writing"
17.07.2024 13:00-14:30 online in BigBlueButton, registration on OPAL
Workshop "ChatGPT as a scientific writing assistant"
08.08.2024 11:00-14:30, presence in Fritz-Foerster-Bau, room 101 Registration on OPAL

Further offers

Offers from other TUD service centers

ZILL: Information website on the didactic use of AI
Studium Generale: Lecture series "Work in progress": AI - Opportunities and risks for employees and their interest groups

Offers of the SLUB

Makerspace: workshops, experiments and exchange from May to July 2024
Courses, workshops and events: SLUB event catalog

Offers from other universities and competence centers

Göttingen Society for Scientific Data Processing (GWDG): Portal with free access to various OpenSource LLMs with TUD login. academiccloud.de
KI-Campus: Learning platform with courses, videos, podcasts and blog entries that can be used after free registration. KI-Campus.org
VK:KIWA: Virtual Competence Center on AI and Research Associates with publications and an overview of AI applications at various stages of the writing process. VK:KIWA.de
Hochschulforum Digitalisierung: Dossier "Generative AI", various contributions
Writing Center of the Goethe University Frankfurt a. M.: Handout"Use of AI writing tools by students"
University of Basel : Guide "Quoting from AI"
Leipzig University Library: YouTube playlist "How to: Wissenschaftliches Arbeiten mit KI". Brief presentation of various AI tools and their potential applications in the academic writing process.

How generative AI can support academic reading and writing

AI tools can be used in every phase of the writing process. Although they do not completely replace human actions, they are suitable, for example ...

for inspiration and brainstorming
for the creation of outline drafts
for help in selecting methods
as an additional research option
for the development of literature networks and summaries
for summaries, translations and help with understanding texts
for data evaluation and visualization
for generating texts (and other media), e.g. from key points or as different versions of the same text section
for text feedback on structure and writing style according to predefined criteria
for correcting spelling and grammar

For more information, see the handout "Use of AI writing tools by students" from the Writing Center at Goethe University Frankfurt am Main.

AI tool tips

Which AI tools can usefully support the academic writing process? What can they do and what can't they do? How do you use them and what do you need to bear in mind with regard to terms of use, copyright and data protection?

Here is the most important information about our (current) favorites:

ChatGPT-4

Brief description	ChatGPT is a pre-trained large language model that generates texts (and other media) in response to user input (prompts) based on its training data. The aim is to statistically calculate linguistic probabilities statistically. Depending on which model is used (GPT 3.5 / GPT-4 / GPT-4 turbo / GPT-4 omni), various multimodal functions are available: Creation and processing of images and documents, sound input and output, advanced statistical data analysis, access to the Internet and more.
Strengths	Above all, OpenAI's models can generate very good texts. The models are excellent collaboration partners that are multilingual. The exchange can enable a change of perspective by using the model as a "sparring partner" to look at problems from different angles. It never tires of generating answers and is always available.
Weaknesses	The models hallucinate information (they "lie") and have no actual understanding of the real world. The output they generate can only be based on the training data used in the resource-intensive training process - reproducing everything they have been given (e.g. biases, racism and discrimination). The powerful models consume a lot of resources (e.g. water and electricity), but the users have no exact insight into the consumption.
Data protection	The situation with regard to data protection and copyright is currently difficult - legal issues have not yet been conclusively clarified. Data protection Since OpenAI stores and uses the data entered (e.g. for further training of the models), no personal data from third parties such as names or addresses may be entered without the consent of the data subjects. This also applies to data collected in the context of research processes (e.g. surveys or interviews). Copyright ChatGPT may use copyrighted content in its training data, but users have no insight into the sources on the basis of which the new texts were generated. Copyright infringement is therefore not excluded and all content must be checked by the users. As a large language model, ChatGPT itself has no copyright to the outputs it generates.
Helpful for ...	Inspiration and brainstorming, creating draft outlines, summaries, translations and help with understanding texts, generating texts (and other media), text feedback on structure and writing style according to predefined criteria, correcting spelling and grammar
Access and website	https://chatgpt.com/ An account is required, chat histories are saved. The paid version currently costs USD 20 per month (as of June 2024)
Further information	Unlocking the Power of Generative AI Models and Systems such as GPT-4 and ChatGPT for Higher Education

Consensus

Brief description	In Consensus, simple questions formulated in English can be entered and a series of scientific texts related to the question asked will be compiled.
Strengths	Open Access All texts displayed are freely accessible and directly linked. Consensus obtains the scientific texts from Semantic Scholar, also an AI-based research tool with a current database of over 200 million scientific sources. Clarity All texts are presented with a sentence that matches the question posed. The abstract can also be displayed and, if desired, a summary of up to 10 texts can be generated in response to the question entered. For yes/no questions, there is also the option of displaying the texts according to the yes-probably-no scheme.
Weaknesses	Limited source base The scientific sources from which Semantic Scholar , and therefore Consensus , draws are largely limited to texts from the English-speaking world. As all the texts displayed are published as open access , there are also no sources from licensed journals. A complete literature search is therefore not possible with this tool. Furthermore, not all scientific disciplines are equally represented. The tool prefers yes/no questions.
Data protection	Irrelevant in this case, as no data is uploaded or personal information disclosed. Even if personal data should be entered as a prompt - every prompt is interpreted by the tool as a research question.
Helpful for ...	Inspiration and idea generation, research processes, development of literature networks, summaries and help with understanding texts
Access and website	https://consensus.app/ The basic functions can be used via the free access, but are limited. With the premium version for currently 8.99 USD per month (as of June 2024), you therefore pay for the unlimited number of GPT-4 summaries or "study snapshots" (short list of key information from a paper).
Further information	How To: Literature research with AI - Consensus // Leipzig University Library

DeepL Translator

Brief description	DeepL is an AI-based translation tool.
Strengths	High translation quality The tool is known for its precise and natural-sounding translations. This is made possible by the use of neural networks and a large amount of training data, among other things. Context The translations aim to always take into account the context of the entire text entered. Different variants can be selected or exchanged in the translations. Close linking At least when translating German-English and English-German, the tool automatically forwards you to DeepL Write if required so that you can continue working on the translated texts directly.
Weaknesses	As with all translation tools, it goes without saying that errors cannot be completely ruled out, e.g. if the language used is very technical. Compared to many other translation tools, however, Deep L Übersetzer is one of the better ones.
Data protection	See data protection at DeepL Write.
Helpful for ...	translations
Access and website	https://www.deepl.com/de/translator Simple translations in (currently) 32 languages are possible in the free version, but are also limited here. The paid Pro version, starting at 7.49 euros (as of June 2024), offers unlimited text translation as well as the translation of entire documents and - here too - "maximum data security".

DeepL Write

Brief description	The AI-supported writing tool enables the optimization of texts in the areas of grammar, spelling, style and expression.
Strengths	User-friendliness The tool is extremely easy to use. Simply open it and get started. The limited selection of functions ensures a clear interface. Functions Texts entered can be edited for simple, business, academic or casual writing styles. You can also select a "tone" (e.g. enthusiastic, diplomatic) and search for synonyms for individual words. Spelling, grammar and punctuation errors are corrected automatically.
Weaknesses	Limited language selection The tool only offers work on German or English texts.
Data protection	Only the DeepL Write Pro version guarantees, among other things, "maximum data security". This means that texts are deleted immediately after processing, are never shared with third parties and are not used to train the models.
Helpful for ...	Revision, correction
Access and website	https://www.deepl.com/de/write The number of possible text optimizations is limited in the free access. The paid Pro version for 10 euros per month (as of June 2024) offers unlimited text optimizations, use of writing styles and alternative suggestions in addition to the above-mentioned guaranteed data protection.

Mimir Mentor

Brief description	Mimir is a tool that simplifies literature research, the writing process and final text correction. It includes a broad set of tools and can: add literature data, search and manage literature, find similar sources and statistics Continue writing, rephrase or change sentences in the editor correct spelling & grammar, avoid filler words and unscientific words and check for gender-appropriate language
Strengths	The three areas (literature, editor and correction) can be used together in one interface and synchronize immediately. Mimir can also be used to detect plagiarism (not in the free version). Texts that have already been written can be uploaded as Word documents for further editing in the Mimir workspace. Mimir can be used in German and English and is optimized for academic writing.
Weaknesses	Not all tools are fully available in the free version. Only 5,000 characters can be generated per month, only 5,000 characters are available per correction and only 100 sources can be managed. There are usage statistics for an overview.
Data protection	Mimir is operated by a German company. All personal data is processed and stored on servers in the EU (Germany). As of March 2024, the reformulation is still running via an access to OpenAI (GPT-4), so the texts are also processed via their external servers (in the future, however, this is to be decoupled). The texts that are written and edited in the editor and in the correction are not saved.
Helpful for ...	Literature research and management, text feedback, revision, correction
Access and website	https://mimir-mentor.com An account is required to be able to save projects. The monthly fees for premium access currently range between 17 and 104 euros (as of June 2024).
Further information	Interview with the founders Sven Tegethoff and Robin Schmitt from Mimir Mentor

Perplexity AI

Brief description	Perplexity AI is a research tool that, like GPT, is operated via chatbot, but bases its answers on a list of linked sources. It can also be asked about uploaded files (texts, images, diagrams).
Strengths	Source information All answers (usually given as theses) are generated on the basis of researched sources. Each answer is accompanied by a list of references with direct links to the sources. The individual theses are linked to specific sources from the list. Up-to-dateness The tool can search the Internet on a daily basis and can therefore also answer very current questions. Although this is not always necessary for academic research, it is certainly a big plus for certain questions, such as those relating to current media discussions. Search filter The tool offers the option of setting search filters, for example to search exclusively for academic sources or to generate text only without referring to sources. However, the filters can only be used if the Pro version of the tool is used. Attachment Files can also be uploaded and queried. Perplexity can also use researched sources for this purpose.
Weaknesses	For academic research, this tool is only worthwhile in the Pro version. In free access mode, you get a colorful mix of sources that are available on the Internet. In the Pro version, however, many of the non-academic results can be filtered out using the Academic search filter, so that it is possible to find useful academic sources. In the compiled sources (usually 10-15) you can find what you are looking for. However, the results are far from a comprehensive overview of research - and here too, of course, you need to check whether each type of source is suitable for your own work (e.g. if you are quoting from a popular science blog).
Data protection	Under Settings, you can determine whether or not uploaded data can be used for further training of the tool. You can exclude your own data from further use with just one click.
Helpful for ...	Research processes, development of literature networks, summaries and help in understanding texts, data evaluation
Access and website	https://www.perplexity.ai/ There is a free and a Pro access for currently 20,- USD per month (as of June 2024). In free access mode, you use the standard Perplexity AI model, while the Pro version allows you to choose between the more powerful AI models such as GPT-4o, Claude-3, Sonar Large and others. In addition, the search filters, which are not insignificant for academic research, are only available in the Pro version.
Further information	YouTube tutorial

SCISPACE

Brief description	SCISPACE is an AI tool for literature research and text comprehension. In addition to researching scientific sources, PDFs can be uploaded and questioned in a targeted manner.
Strengths (selection)	Data basis In response to a question entered, the tool lists a series of texts from (currently) around 280 million scientific sources and presents (among other things) an "insight" that relates the text to the question asked. Unlike Consensus , for example, Scispace also includes sources that are not published as open access, which expands the search results. Copilot The tool offers a range of application options for the researched texts in the so-called "Copilot". This can be asked in a targeted manner about the results or methodology of the texts and write short summaries. In addition, any question can be asked via the chatbot, allowing specific aspects of the text to be highlighted. In addition, the bibliography of the respective source is provided, via which all cited sources are directly linked. The results of the copilot can be saved in the "Notebook". My library The tool also allows you to upload PDFs from your own device. The Copilot can also be used here. This means that even uploaded texts can be sorted and questioned according to results, methodology or other levels of comparison.
Weaknesses	A search with Scispace does not replace a comprehensive database search, nor do the abstracts and insights replace the reading of some texts. As a rule, subject-specific databases are (even) better when it comes to completeness. However, the tool is very well suited for an initial literature overview on a specific topic due to the data basis, the diverse application possibilities for texts and the clarity.
Data protection	As PDFs are uploaded from your own hard disk, the issue of data protection is not insignificant here. Scispace itself therefore describes its high level of commitment to data protection: https://typeset.io/t/security-commitment/
Helpful for ...	Inspiration and idea generation, help in selecting methods, research processes, development of literature networks, summaries and help in understanding texts, data evaluation
Access and website	https://typeset.io/ In the free version, all of the above-mentioned fields of application can be used, albeit to a limited extent. In the premium version, which currently costs USD 12 per month (as at June 2014), all features can be used without limitation and insights are generated from more sources. The Copilot is also based on a better model than the free version.
Further information	Tutorial on the SCISPACE YouTube channel External YouTube tutorial

Textshine

Spelling correction	Textshine corrects spelling, grammar, punctuation and typography of German texts. Texts are not rewritten, i.e. it should not be seen as a substitute for proofreading.
Strengths	In contrast to general purpose models such as ChatGPT, Textshine is optimized for spelling and grammar correction and the associated processes.
Weaknesses	Currently only available for German texts, and only for Word files (.docx format). Textshine is not (yet) optimized for academic texts.
Data protection	The company is based in Austria. The documents are transmitted in encrypted form, processed exclusively for the purpose of order fulfillment and irrevocably deleted immediately afterwards.
Helpful for ...	Revision, correction
Access and website	https://www.textshine.com/#demo User account required, the first 10,000 characters can be revised free of charge; 1,000 characters can be entered again and again free of charge on the homepage. Price packages in the paid version are charged according to the number of characters.
Further information	Introduction of Alexander Seifert (founder)

If you have any further questions, need support or advice, or would like to share examples of best practice, please do not hesitate to contact us.

Consultant for Writing Didactics

Paulina Hösl

Project sTUDy smart, expert for AI & writing

Send email

Contact Information

Writing Center of TU Dresden

work

Visiting address:

Fritz-Foerster-Bau, Floor 5, Room 556 Mommsenstr. 6

01069 Dresden

Show map of this location.

work Tel.

Welcome to TU Dresden