DAL Team at PsyDefDetect: From Supervised Encoders to Hierarchical LLM-RAG for Psychological Defense Detection
Year: 2026
Type: conference-paper
Abstract: The PsyDefDetect shared task focuses on classifying nine psychological defense mechanisms in multi-turn dialogues, a problem complicated by severe label imbalance and the implicit, context-dependent nature of defenses.In this work, we investigate several approaches for dialogue-level defense detection, including supervised baselines and large language model (LLM)-based pipelines.Our primary system is a retrieval-augmented LLM framework with hierarchical prediction and lightweight heuristics for decision calibration.Experiments on the PSYDEFCONV dataset show that LLM-based methods improve overall performance compared to supervised baselines, but still struggle with fine-grained distinctions, especially for minority labels.These findings highlight the challenges of modeling implicit psychological constructs in dialogue.
Authors: Anh Chu, Luong Tran, Dat Do, Phuong Mai, Quynh Le, Cat Can
Institution: VNU University of Engineering and Technology
Language: English
Topic: Mental Health via Writing
Subfield: Social Psychology
Field: Psychology
Domain: Social Sciences
Open Access status: gold
OpenAlex ID: W7166872452