PediaMind-R1: A Temperament-Aware Language Model for Personalized Early Childhood Care Reasoning via Cognitive Modeling and Preference Alignment

TL;DR

PediaMind-R1 is a specialized language model that uses developmental psychology and temperament theory to provide personalized, empathetic caregiving advice for infants and toddlers, demonstrating improved interpretability and reasoning.

Contribution

It introduces a novel temperament-aware training pipeline and evaluation framework for personalized early childhood care reasoning using large language models.

Findings

Accurately interprets early childhood temperament profiles

Proactively engages in individualized reasoning

Enhances logical consistency and domain expertise

Abstract

This paper presents PediaMind-R1, a domain-specialized large language model designed to achieve active personalization in intelligent parenting scenarios. Unlike conventional systems that provide generic suggestions, PediaMind-R1 draws on insights from developmental psychology. It introduces temperament theory from the Thomas-Chess framework and builds a temperament knowledge graph for infants and toddlers (0-3 years). Our two-stage training pipeline first uses supervised fine-tuning to teach structured chain-of-thought reasoning, and then applies a GRPO-based alignment stage to reinforce logical consistency, domain expertise, and empathetic caregiving strategies. We further design an evaluation framework comprising temperament-sensitive multiple-choice tests and human assessments. The results demonstrate that PediaMind-R1 can accurately interpret early childhood temperament profiles and proactively engage in individualized reasoning. This work highlights the value of integrating vertical-domain modeling with psychological theory. It offers a novel approach to developing user-centered LLMs that advance the practice of active personalization in sensitive caregiving contexts.