IC-AnnoMI: In-Context MI Dialogues - GitHub Repository
The IC-AnnoMI repository contains source code and a synthetic dataset generated through in-context zero-shot LLM prompting for mental health and therapeutic counselling. IC-AnnoMI is a project that generates contextual MI dialogues using large language models (LLMs). The project contains source code and a synthetic dataset generated through zero-shot prompts, aiming to address the data scarcity and inherent bias problems in mental health and therapeutic consultation.
Detaillierte Einführung
IC-AnnoMI is an official repository that employs Large Language Models (LLMs) to generate in-context Motivational Interviewing (MI) dialogues. The repository includes a dataset folder with annotated MI dialogues across psychological and linguistic dimensions. It also provides a test set for experiments. The project aims to address scarce data and inherent bias challenges in mental health and therapeutic counselling by leveraging the capabilities of LLMs. The IC-AnnoMI project generates contextual MI dialogues through large language models and provides a synthetic dataset for training and testing MI dialogue systems. The project contains detailed annotation files covering dialogue annotations in psychological and linguistic dimensions, suitable for research in mental health and therapeutic consultation.
MehrDatensatz
HeartLink - Empathetic Psychological Model
HeartLink is an empathetic psychological model that uses a large language model fine-tuned on a large empathetic Q&A dataset. It can perceive users' emotions and experiences during conversations and provide empathetic responses using rich psychological knowledge, aiming to understand, comfort, and support users. The responses include emoji expressions to bridge the gap with users, offering psychological support and help during consultations.
Psy-Insight: Mental Health Counseling Dataset
Psy-Insight is a bilingual, interpretable multi-turn dataset for mental health counseling dialogues. It includes 6,208 rounds of multi-turn counseling dialogues in English and 5,776 rounds in Chinese, annotated with step-by-step reasoning labels and multi-task labels. This dataset is designed to support the application of large language models in mental health and is suitable for tasks such as emotion classification and psychological treatment interpretation.
Question-Level Feature Extraction on DAIC-WOZ Dataset
The DAIC-WOZ dataset contains clinical interviews designed to support the diagnosis of psychological distress conditions such as anxiety, depression, and post-traumatic stress disorder. This repository provides code for extracting question-level features from the DAIC-WOZ dataset, which can be used for multimodal analysis of depression levels.