Table-Augmented Generation
Joseph discusses the challenges of combining large language models with databases, particularly when it comes to extracting meaningful insights from complex queries. He emphasizes the need for a synergistic approach, where natural language processing can enhance database capabilities, allowing for more effective reasoning and summarization. The conversation highlights the potential of table-augmented generation in addressing these issues, ultimately aiming to provide clearer answers to intricate questions.In this clip
From this podcast
Gradient Dissent - A Machine Learning Podcast
Evaluating LLMs with Chatbot Arena and Joseph E. Gonzalez
Related Questions
Do I get it right that a Retrieval Augmented Generation (RAG) system can retrieve data in addition to its training data as discussed in the episode with Cohere co-founder Nick Frosst on building LLM apps for business?
I'm thinking that classical or deep ML solutions have a flaw in that they cannot be extended. For example, if one builds a model and wants to introduce a new feature, typically the model has to be retrained from scratch. So, I'm considering building a Knowledge Graph using LLMs. This knowledge graph would have to include time-dependent data (for example, it should be able to retrieve the "current" President of the USA and also previous presidents if asked). I'm thinking this Knowledge Graph could be used for Retrieval Augmented Generation (RAG) to help with business goals or maybe used with more clever User Interfaces (UIs). I'm not sure how to build or populate this KG and also have a rough idea of how to use it. Can you help me with suggesting particular paths for building and populating this Knowledge Graph?
Do I get it right that a Retrieval Augmented Generation (RAG) system can retrieve data in addition to its training data as discussed in the episode with Cohere co-founder Nick Frosst on building LLM apps for business and the clip Model Evaluation Insights?