Investing in Performance: Fine-tune small models with LLM insights - a CFM case study

Overview: This article presents a deep dive into Capital Fund Management’s (CFM) use of open-source large language models (LLMs) and the Hugging Face (HF) ecosystem to optimize Named Entity Recognition (NER) for financial data. By leveraging LLM-assisted labeling with HF Inference Endpoints and refining data with Argilla, the team improved accuracy by up to 6.4% and reduced operational costs, achieving solutions up to 80x cheaper than large LLMs alone.

In this post, you will learn:

How to use LLMs for efficient data labeling
Steps for fine-tuning compact models with LLM insights
Deployment of models on Hugging Face Inference Endpoints for scalable NER applications

This structured approach combines accuracy and cost-effectiveness, making it ideal for real-world financial applications.

*Model*	*F1-Score (Zero-Shot)*	*F1-Score (Fine-Tuned)*	*Inference Cost (per hour)*	*Cost Efficiency*
*GLiNER*	87.0%	93.4%	$0.50 (GPU) / $0.10 (CPU)	Up to 80x cheaper
*SpanMarker*	47.0%	90.1%	$0.50 (GPU) / $0.10 (CPU)	Up to 80x cheaper
*Llama 3.1-8b*	88.0%	N/A	$4.00	Moderate
*Llama 3.1-70b*	95.0%	N/A	$8.00	High Cost

Capital Fund Management (CFM) is an alternative investment management firm headquartered in Paris, also has teams in New York City and London currently overseeing assets totaling 15.5 billion dollars.

Employing a scientific approach to finance, CFM leverages quantitative and systematic methods to devise superior investment strategies.

CFM explored several approaches to improve financial entity recognition, including zero-shot NER using LLMs and smaller models, LLM-assisted data labeling with Hugging Face Inference Endpoints and Argilla, and fine-tuning smaller models on curated datasets. These approaches not only leverage the versatility of large models but also address the challenges of cost and scalability in real-world financial applications.