AutoPsyC: Automatic Recognition of Psychodynamic Conflicts from Semi-structured Interviews with Large Language Models

2025-03-27

AI Summary

Automated identification of psychodynamic conflicts—enduring, unconscious themes influencing behavior—remains absent in semi-structured clinical interviews. Method: This study introduces the first end-to-end large language model (LLM)-based system for conflict detection, formalizing the task as LLM-amenable through structured prompt engineering tailored to the length and implicitness of 90-minute Operationalized Psychodynamic Diagnosis (OPD) interviews. It integrates parameter-efficient fine-tuning (PEFT), retrieval-augmented generation (RAG), and hierarchical dialogue summarization. Contribution/Results: Evaluated on a real-world dataset of 141 diagnostic interviews, the system achieves significantly higher accuracy than all baselines and ablation models in classifying four core conflict types. It overcomes longstanding bottlenecks in manual scoring, establishing the first scalable, interpretable, and fully automated paradigm for psychodynamic assessment.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval
• Natural Language Processing: (Large) Language Models

Application Category

• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems

Abstract

Psychodynamic conflicts are persistent, often unconscious themes that shape a person's behaviour and experiences. Accurate diagnosis of psychodynamic conflicts is crucial for effective patient treatment and is commonly done via long, manually scored semi-structured interviews. Existing automated solutions for psychiatric diagnosis tend to focus on the recognition of broad disorder categories such as depression, and it is unclear to what extent psychodynamic conflicts which even the patient themselves may not have conscious access to could be automatically recognised from conversation. In this paper, we propose AutoPsyC, the first method for recognising the presence and significance of psychodynamic conflicts from full-length Operationalized Psychodynamic Diagnostics (OPD) interviews using Large Language Models (LLMs). Our approach combines recent advances in parameter-efficient fine-tuning and Retrieval-Augmented Generation (RAG) with a summarisation strategy to effectively process entire 90 minute long conversations. In evaluations on a dataset of 141 diagnostic interviews we show that AutoPsyC consistently outperforms all baselines and ablation conditions on the recognition of four highly relevant psychodynamic conflicts.

Problem

• Automatic recognition of unconscious psychodynamic conflicts from interviews
• Overcoming manual scoring of lengthy semi-structured diagnostic interviews
• Enhancing accuracy in identifying specific psychodynamic conflict types

Innovation

• Uses LLMs for psychodynamic conflict recognition
• Combines parameter-efficient fine-tuning with RAG
• Processes full 90-minute interviews via summarization