N\"urnberg NLP at PsyDefDetect: Multi-Axis Voter Ensembles for Psychological Defence Mechanism Classification

TL;DR

This paper presents a multi-axis voter ensemble approach for classifying psychological defence mechanisms in conversations, achieving top performance in a shared task.

Contribution

It introduces a novel ensemble method combining different axes of models to improve classification accuracy in ambiguous psychological defence detection.

Findings

Achieved F1 score of 0.420 on the test set.

Placed first among 21 teams in the shared task.

Demonstrated the effectiveness of multi-axis voter ensembles.

Abstract

Detecting levels of psychological defence mechanisms in supportive 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. We translate this insight into a 9-voter ensemble spanning three orthogonal axes: class granularity (all nine classes for the gatekeeper, only the eight defence classes for the specialists), training method (generative and discriminative) and base model. The system reaches $F1_{test}{=}.420$ on the hidden test set, placing first among 21 registered teams.