AI RESEARCH
N\"urnberg NLP at PsyDefDetect: Multi-Axis Voter Ensembles for Psychological Defence Mechanism Classification
arXiv CS.AI
•
ArXi:2605.07606v1 Announce Type: cross Detecting levels of psychological defence mechanisms in ive conversations is inherently ambiguous. In the PsyDefDetect shared task at BioNLP 2026 the eight positive defence categories share surface language and differ only in pragmatic function and trained raters reach only moderate inter-annotator agreement. On such a task the decisive lever is not a stronger single model but error independence, since any single representation will waver on the overlapping defence boundaries.