A deliberative council of Gemini agents using absence-based clinical rules achieves 0.382 F1 without fine-tuning and second place overall at 0.406 F1 on defense mechanism classification, with minority-class overrides adding 2.4pp.
A Survey of Large Language Models in Psychotherapy: Current Landscape and Future Directions
6 Pith papers cite this work, alongside 14 external citations. Polarity classification is still indexing.
6
Pith papers citing it
14
external citations · OpenAlex
citation-role summary
background 1
citation-polarity summary
years
2026 6roles
background 1polarities
background 1representative citing papers
Introduces a clean matched benchmark and Dynamic Emotional Signature Graphs (DESG) framework that detects implicit sycophancy via clinical-state transitions and reports a 0.0488 macro-F1 gain over baselines on harmful-risk detection.
A multi-axis 9-voter ensemble for psychological defence mechanism classification wins the PsyDefDetect shared task with F1=0.420.
A three-layer trust framework integrating human, AI, and interaction perspectives is proposed to align multi-stakeholder trust criteria for AI-driven mental health support.
LinguIUTics team applies QLoRA fine-tuning of Qwen3-8B plus stratified CV, minority lexical augmentation, logit bias tuning and ensemble blending to achieve 0.3917 macro F1 (7.7 points above Ministral-8B baseline) on PsyDefDetect 2026.
citing papers explorer
-
UTS at PsyDefDetect: Multi-Agent Councils and Absence-Based Reasoning for Defense Mechanism Classification
A deliberative council of Gemini agents using absence-based clinical rules achieves 0.382 F1 without fine-tuning and second place overall at 0.406 F1 on defense mechanism classification, with minority-class overrides adding 2.4pp.
-
Auditing Stealth Sycophancy in Mental-Health Dialogue: Structured Clinical-State Diagnostics and Clean Matched Benchmarks
Introduces a clean matched benchmark and Dynamic Emotional Signature Graphs (DESG) framework that detects implicit sycophancy via clinical-state transitions and reports a 0.0488 macro-F1 gain over baselines on harmful-risk detection.
-
N\"urnberg NLP at PsyDefDetect: Multi-Axis Voter Ensembles for Psychological Defence Mechanism Classification
A multi-axis 9-voter ensemble for psychological defence mechanism classification wins the PsyDefDetect shared task with F1=0.420.
-
Aligning Human-AI-Interaction Trust for Mental Health Support: Survey and Position for Multi-Stakeholders
A three-layer trust framework integrating human, AI, and interaction perspectives is proposed to align multi-stakeholder trust criteria for AI-driven mental health support.
-
LinguIUTics at PsyDefDetect: Iterative Imbalance-Aware Fine-tuning of Qwen3-8B for Psychological Defense Mechanism Classification
LinguIUTics team applies QLoRA fine-tuning of Qwen3-8B plus stratified CV, minority lexical augmentation, logit bias tuning and ensemble blending to achieve 0.3917 macro F1 (7.7 points above Ministral-8B baseline) on PsyDefDetect 2026.
- VISHC at PsyDefDetect: Mitigating Data Scarcity in Psychological Defense Classification with Context-Aware Synthetic Augmentation