Graphs and Auditing LLMs

Erwan discusses the evolution from working with distributed systems to the current focus on large language models (LLMs) and their auditing. He highlights the application of graphs in understanding algorithms and the importance of transparency in measuring the state of complex networks. The conversation reveals insights into the challenges of inferring information from third-party systems and the implications of bias in AI models.

In this clip
From this podcast
Data Skeptic
Auditing LLMs and Twitter
Related Questions
- 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?

Graphs and Auditing LLMs

In this clip

From this podcast

Data Skeptic

Auditing LLMs and Twitter

Related Questions