Exploring Augmentation and Cognitive Strategies for AI based Synthetic Personae

TL;DR

This paper advocates for using large language models as data augmentation tools with cognitive frameworks to improve the reliability of synthetic personae for human-computer interaction research.

Contribution

It introduces a novel approach of employing LLMs as data augmentation systems combined with cognitive and memory frameworks to enhance synthetic personae.

Findings

Data enrichment improves persona reliability

Episodic memory aids in maintaining context

Self-reflection techniques enhance response consistency

Abstract

Large language models (LLMs) hold potential for innovative HCI research, including the creation of synthetic personae. However, their black-box nature and propensity for hallucinations pose challenges. To address these limitations, this position paper advocates for using LLMs as data augmentation systems rather than zero-shot generators. We further propose the development of robust cognitive and memory frameworks to guide LLM responses. Initial explorations suggest that data enrichment, episodic memory, and self-reflection techniques can improve the reliability of synthetic personae and open up new avenues for HCI research.