SS-GEN: A Social Story Generation Framework with Large Language Models

TL;DR

This paper introduces SS-GEN, a framework that uses large language models to generate personalized social stories for children with ASD, combining hierarchical prompting, human filtering, and fine-tuning smaller models for cost-effective, high-quality results.

Contribution

The paper presents a novel constraint-driven prompting strategy, StarSow, and a pipeline for generating, filtering, and fine-tuning models to produce social stories efficiently and affordably.

Findings

High-quality social stories generated at scale

Comparable results with smaller, fine-tuned models

Cost-effective approach for personalized social story generation

Abstract

Children with Autism Spectrum Disorder (ASD) often misunderstand social situations and struggle to participate in daily routines. Social Stories are traditionally crafted by psychology experts under strict constraints to address these challenges but are costly and limited in diversity. As Large Language Models (LLMs) advance, there's an opportunity to develop more automated, affordable, and accessible methods to generate Social Stories in real-time with broad coverage. However, adapting LLMs to meet the unique and strict constraints of Social Stories is a challenging issue. To this end, we propose SS-GEN, a Social Story GENeration framework with LLMs. Firstly, we develop a constraint-driven sophisticated strategy named StarSow to hierarchically prompt LLMs to generate Social Stories at scale, followed by rigorous human filtering to build a high-quality dataset. Additionally, we introduce quality assessment criteria to evaluate the effectiveness of these generated stories. Considering that powerful closed-source large models require very complex instructions and expensive API fees, we finally fine-tune smaller language models with our curated high-quality dataset, achieving comparable results at lower costs and with simpler instruction and deployment. This work marks a significant step in leveraging AI to personalize Social Stories cost-effectively for autistic children at scale, which we hope can encourage future research on special groups.