How Ramp automated receipt processing with fine-tuned LLMs

What this post added

This post details how Ramp used Modal to fine-tune LLMs for receipt processing. They implemented a custom experimentation framework by setting up Modal functions to train multiple models in parallel, persist weights to Modal volumes, and serve inference endpoints. This approach allowed them to evaluate different model designs efficiently and achieve a 34% reduction in manual receipt intervention. The post also highlights the use of Modal for accelerating LLM batch processing, demonstrating a significant speedup and cost reduction for a PII stripping task.