Hey everyone, I’ve been parsing through the Huggingface website and am having a bit of trouble picking out an LLM inference to help me parse through legal documents. I am not a lawyer, but I would like to understand my rights and how to search for answers to legal questions with concrete answers using an inference.

I have heard a multitude of things around Llama being a privacy nightmare and something about Gerganov ML files? GGMU is also a nebulous term to me and I understand the basics about how a model is trained and validated, but not how to pick one for personal use that isn’t GPT-4.

Any suggestions or things to add on to the discussion?

  • gronjo45OPEnglish
    1·
    10 months ago

    Is there another archetype of Machine Learning technologies that would be better suited to the task of locating useful information enciphered in legalese? I know Lex Machina exists, but that’s more of a specialized software for someone in case law.

    I don’t plan on using what the Agent tells me in a court of law, nor do I plan on using it to blindly form a legal opinion. I remember watching the Legal Eagle video about a lawyer who submitted a legal brief containing case law that didn’t even exist because GPT-4 hallucinated it! Sounds like a nightmarish scenario to find yourself losing your J.D. over it lol

    • mo_ztt ✅@lemmy.worldEnglish
      3·
      10 months ago

      I think an LLM+Chroma is probably as good as it gets, and who knows, it might work. Just I’d be very careful of getting screwed by the process. As I’m sure you know LLMs are right at that inflection point where they’re good enough to seem trustworthy but they can still completely malfunction (and they tend to do so in ways that are actually really difficult to spot because they seem perfectly plausible.)

      Yeah the Legal Eagle video was hilarious. The guy used GPT-4 to make his legal briefs, then when it hallucinated cases he lied to the judge and said he’d researched them and the cases existed, then when faced with the clearly obvious fact that they didn’t, he finally came clean but still sort of tried to weasel out of responsibility for the whole thing and the judge quite rightly tore him a new one. And, I have some vague memory of it being discovered that GPT had basically tried to tell him it wasn’t qualified to make his legal briefs and he insisted to it that it needed to do it anyway. It was just an absolute casserole from start to finish.