We introduce MALADE (Multiple Agents powered by LLMs for ADE Extraction), a multi-agent system for Pharmacovigilance. It is the first effective explainable multi-agent LLM system for extracting Adverse Drug Events (ADEs) from FDA drug labels and drug prescription data.
LLMs are increasingly being used to let users converse in natural language with a variety of types of data sources:
Transformer-based language models are fundamentally next-token predictors, so naturally all LLM APIs today at least provide a completion endpoint. If an LLM is a next-token predictor, how could it possibly be used to generate a response to a question or instruction, or to engage in a conversation with a human user? This is where the idea of "chat-completion" comes in. This post is a refresher on the distinction between completion and chat-completion, and some interesting details on how chat-completion is implemented in practice.
There are commercial, remotely served models that currently appear to beat all open/local models. So why care about local models? Local models are exciting for a number of reasons:
Given the remarkable abilities of recent Large Language Models (LLMs), there is an unprecedented opportunity to build intelligent applications powered by this transformative technology. The top question for any enterprise is: how best to harness the power of LLMs for complex applications? For technical and practical reasons, building LLM-powered applications is not as simple as throwing a task at an LLM-system and expecting it to do it.