SubmissionNumber#=%=#7
FinalPaperTitle#=%=#UTS at PsyDefDetect: Multi-Agent Councils and Absence-Based Reasoning for Defense Mechanism Classification
ShortPaperTitle#=%=#
NumberOfPages#=%=#
CopyrightSigned#=%=#
JobTitle#==#
Organization#==#
Abstract#==#This paper describes our system for classifying psychological defense mechanisms in emotional support dialogues using the Defense Mechanism Rating Scales (DMRS), placing second (F1 0.406) among 63 teams.1 A central insight is that defense mechanisms are defined by what is absent - missing affect, blocked cognition, denied reality. We encode this as an affect-cognition integration spectrum in prompt-level clinical rules, which account for the largest single gain (+11.7pp F1).
Our architecture is a multi-phase deliberative council of Gemini 2.5 agents where class-specific advocates rate evidence strength rather than voting—achieving F1 0.382 with no fine-tuning, a top-5 result among 63 teams on its own. We find, however, that the council is confidently wrong about minority classes: 59–80% of stable minority predictions are incorrect, driven by a systematic "L7 attractor" in which emotional content defaults to the majority class. A targeted override ensemble from three fine-tuned Qwen3.5 models corrects 16 of these errors (+2.4pp), selected by a structured multi-agent system (builder, critic, regression guard) that produced a larger F1 gain in one iteration than 8 prior attempts combined.
Author{1}{Firstname}#=%=#Dima
Author{1}{Lastname}#=%=#Galat
Author{1}{Username}#=%=#thedima
Author{1}{Orcid}#=%=#
Author{1}{Email}#=%=#dima.galat@student.uts.edu.au
Author{1}{Affiliation}#=%=#UTS
Author{2}{Firstname}#=%=#Marian Andrei
Author{2}{Lastname}#=%=#Rizoiu
Author{2}{Orcid}#=%=#
Author{2}{Email}#=%=#Marian-Andrei.Rizoiu@uts.edu.au
Author{2}{Affiliation}#=%=#UTS

==========
èéáğö