CREATE INTERACTIVE WORKSHOP

CREATE organizes interactive workshops each year. Prominent experts within the field of Health Psychology are invited to lead these workshops. The overall aim of these workshops is to enhance the knowledge and skills of early-career researchers working in Health Psychology.

The CREATE pre-conference workshop is a separate format from the conference workshops, and registration follows its own procedure.

Sun 30th and Mon 31st of August 2026 (+ social activity on Sun 30th August)

Application: Please apply here for the pre-conference workshop. Deadline for applications is May 26th, 2026.

Artificial intelligence is rapidly transforming how research is conducted. This hands-on workshop introduces early-career researchers to practical ways to use large language models (LLMs) rigorously and responsibly in evidence synthesis. Focusing on systematic review workflows, participants will learn how to develop effective system instructions and prompts, generate structured summaries to support screening decisions using chain-of-thought prompting, and improve data extraction accuracy through expert-informed few-shot prompting. The workshop will also address key limitations of LLMs, including issues such as context degradation (“context rot”) and positional bias, and discuss practical strategies for mitigating these challenges in applied research settings. Led by Ian Kellar and João Craveiro, the session combines methodological guidance with applied exercises. Participants will work through concrete examples and develop prompts that can be directly implemented in their own review projects. No prior technical or programming experience is required.

The workshop is not only about developing practical skills but also about connecting. Expect to meet like-minded early-career researchers and learn more about the EHPS before the conference even officially begins. Organized by CREATE, a subdivision of the EHPS, the workshop opens the door to how AI can be used in evidence synthesis. Join us to move beyond experimentation with AI and toward more transparent, thoughtful, and methodologically sound applications in scientific practice.