UTS at PsyDefDetect: Multi-Agent Councils and Absence-Based Reasoning for Defense Mechanism Classification

TL;DR

This paper presents a multi-agent system for classifying psychological defense mechanisms in dialogues, emphasizing the importance of absence cues and achieving competitive results without fine-tuning.

Contribution

Introduces a novel multi-agent council architecture and absence-based prompt rules for defense mechanism classification, improving performance and interpretability.

Findings

Achieved second place with F1 0.406 among 64 teams.

Absence-based prompt rules significantly improved classification accuracy (+11.4pp F1).

A targeted override ensemble increased F1 by 2.4pp using structured multi-agent strategies.

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 64 teams. 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 (+11.4pp 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 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 applies 16 overrides (+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.