Improving Your Scientific Writing with AI

Aims

In this workshop, you will:

• identify and evaluate use cases for deploying AI legally and ethically;
• create personalized LLM prompts and skills for eliciting feedback on the different phases of writing, from argument and logical structure to copyediting and stylistic refinement;
• critically assess AI feedback against the epistemic demands of scientific writing (precision, hedging, claim calibration, reproducibility);
• apply these techniques to improve a piece of your own scientific writing.

Content

This hands-on workshop helps you develop personalized methods for using AI throughout the revising process-from reshaping arguments and logical structure to refining style and language. You will build your own prompts and reusable skills, practice critically assessing AI feedback, and apply these techniques to a piece of your own scientific writing. Discussions will address the epistemic demands of scientific writing (precision, hedging, claim calibration, reproducibility) as well as current AI policies at the university and in scientific publishing. Come prepared to share experiences with colleagues, experiment with tools, and leave with a revised draft and a workflow you can keep using.

Methods

The workshop will include input segments by the trainer, hands-on exercises, peer discussion, and live demos of prompts and tools by the participants. Between the sessions, you will apply the techniques to your own writing and prepare to share the results in the second meeting.

Target Group

All doctoral Candidates of the Faculty of Science

Requirements

Please bring a laptop with access to an LLM chatbot (e.g., Claude, ChatGPT, Le Chat, etc.) and an AI writing assistant (LanguageTool, DeepL Write, Grammarly) of your choice. If possible, also select a text or a section of a text you would like to work on in the workshop.

About the Trainer

Dr. Anthony Mahler is a scientific copyeditor and writing coach at the University of Basel Language Center. He has contributed to various university AI initiatives, including the 2024 lecture series Academic Writing with Digital Tools and the 2025 SciLib Forum: AI Meets Scientific Writing.

Workload

Preparation: 2.5h
Course attendance: 4.5h

Feature

This course is reserved for doctoral candidates of the Faculy of Science.

Once registration is open, applications will be collected for 24 hours and course places allocated by lot. All registrations received after the initial 24h period will be put on a waiting list and assigned on a first come, first served basis.

Course places/places on the waiting list will be confirmed by e-mail. Course registrations can only be canceled before the registration period ends (send an e-mail to grace@unibas.ch). Full course attendance is mandatory. Participants who fail to attend a course without prior notification or withdraw after the registration deadline are subject to a fee of CHF 30. In addition, participants who cancel their course registration at a later point in time, are absent without an excuse or do not attend the entire course will, for reasons of fairness, not be considered for course registration in the following semester and will be removed from other courses offered in the same semester. Please find the detailed regulations on the Transferable Skills Homepage.