Evaluation Techniques for Large Language Models – Rajiv Shah, former Hugging Face, currently Snowflake

Large language models (LLMs) represent an exciting trend in AI, with many new commercial and open-source models released recently. However, selecting the right LLM for your needs has become increasingly complex.
Data Innovation Summit 2024 Data Innovation Summit 2024
Data Innovation Summit 2024

Session Outline

Large language models (LLMs) represent an exciting trend in AI, with many new commercial and open-source models released recently. However, selecting the right LLM for your needs has become increasingly complex. This talk at the Data Innovation Summit 2024, involved Rajiv Shah, Data Cloud Principal, AI/ML at Snowflake! In his talk, Rajiv provides data scientists and machine learning engineers with the latest knowledge and tools for evaluating and choosing LLMs.

Key Takeaways

  • The problems with the current state of evaluation tools/metrics
  • The four approaches for evaluating LLMs
  • Applying these to building a question/answer application

Moreover, in a recent interview, In an interview, Rajiv provides a glimpse into Hugging Face’s role in revolutionizing the open-source AI community. As now a former key figure at Hugging Face, Rajiv was focused on addressing complex challenges using open-source AI.

Add a comment

Leave a Reply