The Mostly Unstructured Podcast

S2 Ep5: Does a business have any business training an LLM?

Listen Later

Enterprise LLMs: RAG vs Fine‑Tuning, IDP & Governance

In this episode of the Mostly Unstructured podcast, Ed and Clay discuss whether it’s better to train a domain‑specific LLM or leverage foundational models like ChatGPT, Gemini and Claude. They explain the trade‑offs between fine‑tuning and retrieval‑augmented generation (RAG), and why Intelligent Document Processing (IDP) is vital for turning unstructured data into usable context.

In this discussion, we cover:

  • Why training your own LLM is risky and often unnecessary compared to adopting and building from a foundational model.
  • How retrieval‑augmented generation (RAG) delivers more accurate results than simple fine‑tuning.
  • The importance of Intelligent Document Processing (IDP) for ingesting unstructured data and building domain context.
  • Real‑world lessons on AI governance, including the Air Canada bereavement‑policy chatbot case.
  • Managing bias, hallucinations and toxicity in enterprise models.
  • Measuring your return on AI investment.

    • For those thrown by the excessive acronyms, let's define:
    LLM = Large Language Model
    RAG = Retrieval‑Augmented Generation
    IDP = Intelligent Document Processing.
     
    For more insights on enterprise AI for data intelligence, visit our website and read our blog on training an LLM referenced in the episode.

    Website: https://www.keymarkinc.com/
    Blog: https://www.keymarkinc.com/how-to-tra... 

    ...more
    View all episodesView all episodes
    Download on the App Store
    The Mostly Unstructured PodcastBy The Mostly Unstructured Podcast
    • 5
    • 5
    • 5
    • 5
    • 5

    5

    7 ratings