How to use LLMs for Fact Checking

Поделиться
HTML-код
  • Опубликовано: 7 ноя 2024

Комментарии • 13

  • @leobeeson1
    @leobeeson1 2 месяца назад +1

    Great video. A few caveats: When working with documents which can be found online (potentially in the LLM's training data) it would not be clear if the LLM is picking up the errors from the context (whether full text or retrieved chunks) or from memory. This is important if you're building a system and you need to be sure it's identifying errors by inferring from context and not from what it thinks it knows, such as when your corpora come from proprietary data. If the LLM is leveraging what it knows from parametric memory more than inferring from context, then the quality would be significantly lower (as it has no memory of this data).

  • @fabioaloisio
    @fabioaloisio 2 месяца назад +1

    As always good job Ronan! Some planning for a custom impl of MoA?

    • @TrelisResearch
      @TrelisResearch  2 месяца назад +1

      Cheers Fabio, what do you mean by MoA? Mixture of Agents?

    • @fabioaloisio
      @fabioaloisio 2 месяца назад

      Yep! Would be very insteresting! Tks

  • @AI-Doom-
    @AI-Doom- 2 месяца назад +1

    Bro is cooking with the thumbnails.

    • @TrelisResearch
      @TrelisResearch  2 месяца назад

      You like those? Or too much… better to go back raw dawg?

    • @AI-Doom-
      @AI-Doom- 2 месяца назад

      @@TrelisResearch No, they are awesome! They made me want to click the video immediately.

  • @pim8268
    @pim8268 2 месяца назад

    Wow this video was amazing. Thank you for showing the pressure Testing and the needle on a haystack stuff. Great video!

  • @danielsaberi3812
    @danielsaberi3812 2 месяца назад +2

    Thanks! Very interesting comparison!
    Maybe having a custom splitting function that "splits the text by facts" and then a retrieval process just as you demonstrated (split by pages) could be an improvement?

    • @TrelisResearch
      @TrelisResearch  2 месяца назад +2

      Yeah definitely doing better chunking would help

  • @maxpayne8708
    @maxpayne8708 Месяц назад

    COuld you please do a vide on Graph RAG/ Knowledge graphs? Thanks.

    • @TrelisResearch
      @TrelisResearch  Месяц назад

      Will take a look again at Graph RAG, I did get that request before too. I'll add to my notes