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.
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.
The data is originally source from (Sun et al,2021). (Liu et al, 2023) processed the data to make it a dataset vis huggingface api with taining/validation/testing splitting
The ToM QA Dataset is designed to evaluate question-answering models' ability to reason about beliefs. It includes 3 task types and 4 question types, creating 12 total scenarios. The dataset is inspired by theory-of-mind experiments in developmental psychology and is used to test models' understanding of beliefs and inconsistent states of the world.
The Chinese Psychological QA DataSet is a collection of 102,845 community Q&A pairs related to psychological topics., providing a rich source of data for research and development in psychological counseling and AI applications. Each entry includes detailed question and answer information, making it a valuable resource for understanding user queries and generating appropriate responses.