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

2026-01-11

arXiv.org

AI Summary

This work addresses a critical gap in mental health–oriented function-calling datasets: the lack of support for physiological signals from wearable devices, which hinders structured interaction with large language models (LLMs) in this domain. To bridge this gap, the authors construct a synthetic dataset that maps natural language queries—spanning explicit, implicit, behavioral, symptomatic, and metaphorical expressions related to sleep, activity, cardiovascular health, stress, and metabolism—to standardized health API calls. Each mapping includes query category, reasoning steps, temporal parameters, and target functions. The methodology integrates LLM-driven data generation, the FHIR health data standard, structured natural language–to–API mapping, and temporal normalization. This dataset enables, for the first time, intent grounding and temporal reasoning for mental health LLM agents over wearable-derived data, filling a key void in controllable and reproducible research. The dataset is publicly released.

Technology Category

• Humans and AI: Interaction Techniques and Devices
• Application Domains: Humanities & Computational Social Science
• Natural Language Processing: Code Generation / Program Synthesis from Natural Language

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Search and Retrieval-Augmented AI: Agentic search

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.

Problem

• mental health
• function calling
• wearable sensor data
• large language models
• health data schema

Innovation

• function calling
• mental health
• wearable sensors
• large language models
• synthetic dataset