SubmissionNumber#=%=#25
FinalPaperTitle#=%=#KCL-Cogstack at PsyDefDetect: A Hierarchical Approach to Detecting Defense Mechanisms in Supportive Dialogue
ShortPaperTitle#=%=#
NumberOfPages#=%=#
CopyrightSigned#=%=#
JobTitle#==#
Organization#==#
Abstract#==#We present our system for the PsyDefDetect shared task, which focuses on detecting and classifying psychological defense mechanisms in peer emotional support conversations. Our core contribution is a hierarchical classification framework that structures prediction as a coarse-to-fine pipeline over a clinically validated label 
hierarchy, grounded in the Defense Mechanism Rating Scales (DMRS). Through systematic experimentation with flat fine-tuning, few-shot prompting, and hierarchical classification, we demonstrate that explicitly modelling the structured relationships among defense levels offers a more effective alternative to flat classification, achieving a macro F1 of 0.23 on the official test set.
Author{1}{Firstname}#=%=#Shubham
Author{1}{Lastname}#=%=#Agarwal
Author{1}{Username}#=%=#ssagarwal
Author{1}{Orcid}#=%=#
Author{1}{Email}#=%=#shubham.agarwal@kcl.ac.uk
Author{1}{Affiliation}#=%=#King's College London
Author{2}{Firstname}#=%=#Thomas
Author{2}{Lastname}#=%=#Searle
Author{2}{Orcid}#=%=#
Author{2}{Email}#=%=#thomas.searle@kcl.ac.uk
Author{2}{Affiliation}#=%=#King's College London
Author{3}{Firstname}#=%=#Richard
Author{3}{Lastname}#=%=#Dobson
Author{3}{Orcid}#=%=#
Author{3}{Email}#=%=#richard.j.dobson@kcl.ac.uk
Author{3}{Affiliation}#=%=#King's College London

==========
èéáğö