Exploring the Readiness of Prominent Small Language Models for the Democratization of Financial Literacy

TL;DR

This paper evaluates small language models for their potential to democratize financial literacy by analyzing their performance, resource usage, and accessibility in providing financial question answering capabilities.

Contribution

First comprehensive assessment of open-source small language models for financial literacy support, focusing on accessibility, performance, and readiness for democratization.

Findings

Some models show promise for fine-tuning and deployment.

Memory usage and inference times vary significantly across models.

Certain models are limited in output readability and accuracy.

Abstract

The use of small language models (SLMs), herein defined as models with less than three billion parameters, is increasing across various domains and applications. Due to their ability to run on more accessible hardware and preserve user privacy, SLMs possess the potential to democratize access to language models for individuals of different socioeconomic status and with different privacy preferences. This study assesses several state-of-the-art SLMs (e.g., Apple's OpenELM, Microsoft's Phi, Google's Gemma, and the Tinyllama project) for use in the financial domain to support the development of financial literacy LMs. Democratizing access to quality financial information for those who are financially under educated is greatly needed in society, particularly as new financial markets and products emerge and participation in financial markets increases due to ease of access. We are the first to examine the use of open-source SLMs to democratize access to financial question answering capabilities for individuals and students. To this end, we provide an analysis of the memory usage, inference time, similarity comparisons to ground-truth answers, and output readability of prominent SLMs to determine which models are most accessible and capable of supporting access to financial information. We analyze zero-shot and few-shot learning variants of the models. The results suggest that some off-the-shelf SLMs merit further exploration and fine-tuning to prepare them for individual use, while others may have limits to their democratization.