Join our list for notifications and early access to events
Today we're joined by Armineh Nourbakhsh of JP Morgan AI Research to discuss the development and capabilities of DocLLM, a layout-aware large language model for multimodal document understanding. Armineh provides a historical overview of the challenges of document AI and an introduction to the DocLLM model. Armineh explains how this model, distinct from both traditional LLMs and document AI models, incorporates both textual semantics and spatial layout in processing enterprise documents like reports and complex contracts. We dig into her team’s approach to training DocLLM, their choice of a generative model as opposed to an encoder-based approach, the datasets they used to build the model, their approach to incorporating layout information, and the various ways they evaluated the model’s performance.
One Response
It would be great if you could boost the volume a bit. Especially with Armineh Nourbakhsh, you both used your quiet “library” voices. Listening to the podcast on my mp3 player in the gym, I just could not follow the conversation. Whereas, The Cognitive Revolution podcasts are louder and do fine. It’s always possible for a listener to turn the volume down, but if it is not there in the first place, they’re stuck. I can boost the volume myself using an audio tool, but this is a pain.
Anyway, Thank you for the podcast. Great content! And I appreciate your informed questions and willingness to let the guest carry on at length when they are on a roll.