mind_call: A Dataset for Mental Health Function Calling with Large Language Models

TL;DR

This paper introduces a synthetic dataset for mental health function calling with LLMs, enabling better understanding and interaction with wearable health data for mental health support.

Contribution

The paper presents a novel, publicly available dataset that maps natural language queries to standardized health data API calls for mental health applications.

Findings

Supports research on intent grounding and temporal reasoning

Enhances LLM-based mental health assistance capabilities

Facilitates reliable function invocation in health data interactions

Abstract

Large Language Model (LLM)-based systems increasingly rely on function calling to enable structured and controllable interaction with external data sources, yet existing datasets do not address mental health-oriented access to wearable sensor data. This paper presents a synthetic function-calling dataset designed for mental health assistance grounded in wearable health signals such as sleep, physical activity, cardiovascular measures, stress indicators, and metabolic data. The dataset maps diverse natural language queries to standardized API calls derived from a widely adopted health data schema. Each sample includes a user query, a query category, an explicit reasoning step, a normalized temporal parameter, and a target function. The dataset covers explicit, implicit, behavioral, symptom-based, and metaphorical expressions, which reflect realistic mental health-related user interactions. This resource supports research on intent grounding, temporal reasoning, and reliable function invocation in LLM-based mental health agents and is publicly released to promote reproducibility and future work.