Integrating LLMs in the Questionnaire Design Process

Integrating LLMs in the Questionnaire Design Process by Dr Caroline Roberts and Professor Patrick Sturgis

Effective questionnaire design remains one of the greatest challenges in survey research, requiring a mix of artistic skill, scientific expertise, and thorough evaluation and testing procedures to minimise measurement errors in the data produced. Increasingly powerful Large Language Models offer researchers new ways to support the questionnaire development process, along with substantial gains in cost efficiency. However, the integration of LLM’s in questionnaire design, evaluation and testing (QDET) procedures should be handled in a critical way, based on knowledge of the scientific principles and craft of effective social measurement, as well as of optimal prompt engineering methods.

This workshop aims to a) present an overview of persistent challenges in QDET; b) demonstrate different ways in which LLMs can be used to address these; and c) explore opportunities and tactics for future applications of GenAI in QDET aimed both at facilitating procedures for researchers but also improving survey measurement quality.

Session Details
Time: 10:00 - 15:00 (12:00 - 13:00 Lunch break)
Date: 3 December 2025
Mode: Hybrid - Online via Zoom and in person at CON 1.01

If you are an ESRC funded student then we require your name, email and course to report your attendance to your home institution, please click here to see the privacy notice that this data collection is subject to.