Matthew Harris

AI assisted research using FEMA disaster response documents Matthew Harris · Follow Published in Towards Data Science · 16 min read · 3 hours ago — STORM researches the topic via perspective-guided question asking in simulated conversations. Source TL;DR The use of LLM agents is becoming more common for tackling multi-step long-context research tasks where traditional RAG direct prompting methods can sometimes struggle. In this article, we will explore a new and promising technique developed

Matthew Harris · Follow Published in Towards Data Science · 29 min read · 12 hours ago — Source: GPT-4o TL;DR In the humanitarian response world there can be tens of thousands of tabular (CSV and Excel) datasets, many of which contain critical information for helping save lives. Data can be provided by hundreds of different organizations with different naming conventions, languages and data standards, so having information (metadata) about what each column represents in

Matthew Harris · Follow Published in Towards Data Science · 17 min read · 11 hours ago — TL;DR There are lots of tutorials on using powerful Large Language Models (LLMs) for knowledge retrieval. However, if considering real-world application of these techniques, engineering best practices need to be applied and these should be extended to mitigate some of the new risks associated with LLMs, such as hallucinations. In this article, we explore how to implement