Comment by ChuckMcM

It does that all the time even now. Play with temp, top_k, min_p and nothing is preventing you from getting combinations and order of tokens previously not encountered in history.

A language model can generate valid sentences that have never existed before -- not just syntactically or statistically valid sentences in a Markovian sense, but semantically valid ones. How could it possibly do that without an implicit awareness of all aspects of language, including grammar and parts of speech?

That implicit awareness is indistinguishable from knowledge, at least to the extent it yields correct results.

And the fact that it was inferred from examples rather than taught explicitly is indistinguishable from intelligence.

I did eventually get an LLM to produce what seems to be a correct diagram of a sentence it had never seen, but it took about ten tries. Grammatical analysis seems to have happened correctly every time, but getting to a usable diagram was difficult.

(I know that it's generally rude to include LLM output in HN comments, but in this case I think it's essential supporting material to elevate the discussion of LLM capabilities above "yes it is", "no it isn't".)

First, I just asked ChatGPT (GPT-4o mini, what they offer anonymous free users):

> Please diagram the sentence, "If my mother's road had been cultural, my uncle's sloth squad residue would have compiled a periodic meadow of night."

I just invented that sentence, picking several words with a random number generator, but of course I can't prove to you that I didn't copy it from some book you haven't seen. (For that, you'd have to invent a sentence yourself, or at least provide me with some words to include in it.) I hope you can at least agree that it's a highly unlikely sentence for anyone ever to have uttered before!

After talking to itself for a few paragraphs, it arrived at the following grammatical analysis:

  Step 4: Diagramming the sentence

    Main Clause:
        Subject: "my uncle's sloth squad residue"
        Verb: "would have compiled"
        Direct Object: "a periodic meadow of night"
            "a periodic meadow" (noun phrase)
            "of night" (prepositional phrase modifying "meadow")

    Conditional Clause:
        Subject: "my mother's road"
        Verb: "had been" (linking verb)
        Predicate Adjective: "cultural"

                If
        ______/______
       |              |
    my mother's    had been
      road             |
                        cultural
       
   my uncle's sloth squad residue
                 |
    would have compiled
                 |
  a periodic meadow of night
              |
            of
            night

                 If
           _______/______
          |               |
  my mother's road    had been
           |             |
       cultural      (Main Clause)
                       |
       my uncle's sloth squad residue
                           |
                 would have compiled
                           |
               a periodic meadow
                         |
                       of night

  1. **Identify the main clauses**: 
     - "If my mother's road had been cultural" is a dependent clause (specifically, a conditional clause).
     - "my uncle's sloth squad residue would have compiled a periodic meadow of night" is the main clause.

  2. **Start with the main clause**:
     - Subject: "my uncle's sloth squad residue"
       - "my uncle's" modifies "sloth squad," which in turn modifies "residue."
     - Predicate: "would have compiled"
       - This includes the modal auxiliary verb ("would"), perfect auxiliary ("have"), and main verb ("compiled").
     - Direct object: "a periodic meadow of night"
       - “a” is an article modifying “meadow,”
       - “periodic” modifies “meadow,”
       - “of night” is a prepositional phrase modifying “meadow.”

  3. **Diagram the dependent clause**:
     - Subject: "road"
       - Modified by possessive noun phrase “my mother’s”
     - Predicate: "had been"
     - Complement/Adjective: "cultural"

But then it came up with the following incorrect diagram:

                            +---------------------------------------------------+
                            |                      Main Clause                   |
                            +---------------------------------------------------+
                                    /                |               \
                                   /                 |                \
                                  /                  |                 \
                         [My uncle's]         [sloth squad]          [residue]
                             \                    /                     /
                              \                  /                     /
                               \                /                     /
                                would have compiled -------------------
                                                  \
                                                   \
                                                    \
                                                     [a periodic meadow of night]
                                                      /           |            \
                                                     /            |             \
                                                    a        periodic       [of night]

  +---------------------+
  |  Dependent Clause   |
  +---------------------+
        If
         |
        road
      ___|_____
    |          |
   my mother's had been cultural

But my conclusion from this is not that GPT-4 can't analyze the grammatical structure of sentences it had never seen. It's that GPT-4 gets "confused" when it tries to draw ASCII art, like a person trying to tell you how to draw it over the telephone, but not quite as bad. I've seen similarly abominable results when it tried to draw circuit schematics and guitar tablatures as ASCII art. I tried asking it for a graphviz diagram, which was syntactically correct graphviz code but didn't express the sentence structure properly.

I tried simplifying the problem with the prompt, 'Please provide a syntactic tree showing the syntactic derivation of the sentence, "My uncle's sloth squad residue would have compiled a periodic meadow of night," using graphviz syntax and with individual words at the leaf nodes of the tree.' which yielded a slightly incorrect diagram. (I'm still sure nobody has ever uttered this sentence before.) On being told, "This diagram is not quite right.", GPT-4 produced the following diagram, which I believe is correct except for an extra "s" on "uncle" (you can see this in your browser at https://is.gd/Axufjx):

  digraph G {
      node [shape=plaintext];

      S [label="S"];
      NP [label="NP"];
      VP [label="VP"];

      S -> NP;
      S -> VP;

      // Noun Phrase breakdown
      DP_my [label="DP"];
          DP_my -> My;

      UnclePossessive [label="NP"];
          UnclePossessive -> Uncles;
          UnclePossessive -> ApostropheS;

          NP -> DP_my;
          NP -> UncleCompound;

      UncleCompound [label="NP"];
          SlothSquadResidue[label = "N'"];
              SlothSquadResidue-> Sloth;
              SlothSquadResidue-> SquadResidue;

              SquadResidue[label = "N'"]
                  SquadResidue-> Squad;
                  SquadResidue-> Residue;

              UncleCompound-> UnclePossessive;
              UncleCompound-> SlothSquadResidue;


      // Verb Phrase breakdown
       ModalWould[label = "Modal"];
       ModalWould-> Would;

       AuxHave[label = "Aux"];
       AuxHave-> Have;

       VCompiled[label = "V"];
       VCompiled-> Compiled;

       ObjectNP[label = "NP"];  // Direct object noun phrase
           ArticleA[label = "D"];
           ArticleA-> A;

           MeadowPhrase[label = "N'"];  // 'Meadow' modified by 'periodic'
               AdjPeriodic[label = "Adj"];
               AdjPeriodic-> Periodic; 

               MeadowWord[label = N];
               MeadowWord -> Meadow; 

               MeadowPhrase -> AdjPeriodic; 
               MeadowPhrase -> MeadowWord; 

           PPofNight[label = PP];  // Prepositional phrase 'of night'
               PrepOf[label=P]
                   PrepOf-> Of; 

                   NightNounPhrase[label=N]
                       NightNounPhrase-> Night; 

                   PPofNight -> PrepOf; 
                   PPofNight -> NightNounPhrase; 

           ObjectNP -> ArticleA; 
           ObjectNP -> MeadowPhrase; 
           ObjectNP -> PPofNight;


       VP -> ModalWould;
       VP -> AuxHave;
       VP -> VCompiled
       VP -> ObjectNP

  }

  digraph SyntacticTree {
    node [shape=plaintext];

    S -> NP1;
    S -> VP;

    NP1 -> DET1 [label="Det"];
    NP1 -> NP2 [label="NP"];

    NP2 -> NP3 [label="NP"];
    NP2 -> N1 [label="N"];

    NP3 -> N2 [label="N"];
    NP3 -> POS [label="Pos"];

    VP -> AUX1 [label="Aux"];
    VP -> AUX2 [label="Aux"];
    VP -> V [label="V"];
    VP -> NP4 [label="NP"];

    NP4 -> DET2 [label="Det"];
    NP4 -> ADJ [label="Adj"];
    NP4 -> N3 [label="N"];
    NP4 -> PP [label="PP"];

    PP -> P [label="P"];
    PP -> NP5 [label="NP"];

    NP5 -> N4 [label="N"];

    DET1 -> "My";
    N2 -> "uncle";
    POS -> "'s";
    N1 -> "sloth";
    N1 -> "squad";
    N1 -> "residue";
    AUX1 -> "would";
    AUX2 -> "have";
    V -> "compiled";
    DET2 -> "a";
    ADJ -> "periodic";
    N3 -> "meadow";
    P -> "of";
    N4 -> "night";
  }

So LLMs didn't perform nearly as well on this task as I thought they would, but they also performed much better than you thought they would.