MIRROR@IberLEF2026: Call for Participation in AI Challenge

Deadline: May 11th

Participate in MIRROR@IberLEF2026 challenge to develop AI methods for creating synthetic conversation turns to improve behavior code recognition in motivational interviews.

The MIRROR@IberLEF2026 challenge is now online, inviting the community to develop Generative AI methods for creating synthetic conversation turns to improve the performance of models trained to recognize behavior codes in motivational interviews.

The task involves producing high-quality datasets representing diverse clinical conversations to enhance the performance of a baseline model used for behavior code classification.

• Participants are expected to provide three datasets of at most 100 labeled conversation turns.
• The fine-tuned models will be used to make predictions for a hold-out dataset.
• The considered pairs of behavior codes are: Simple reflection vs. Complex reflection, Open question vs. Closed question, and Persuasion vs. Giving Information.

Register and submit your work at https://www.mirror-iberlef.lat/dashboard.

Tags: MIRROR@IberLEF2026, Generative AI, Motivational Interviewing, AI Challenge, Synthetic Conversation Turns, Behavior Code Classification