• oce 🐆
    link
    fedilink
    English
    arrow-up
    1
    ·
    6 个月前

    It would not be a fully determining schema that could apply to random outputs, I would guess this is impossible for natural language, and if it is possible, then it may as well be used for procedural generation. It would be just enough to make an LLM output be good enough. It doesn’t need to be perfect because human output is not perfect either.

      • oce 🐆
        link
        fedilink
        English
        arrow-up
        1
        ·
        6 个月前

        But it also doesn’t need to be as exact as SQL, which removes some kind of complexity.