Spiegare al modello il suo ragionamento

Quando chiedi al modello di spiegare il suo ragionamento, il modello risponde con i passaggi che utilizza per risolvere il problema. Seguire questo processo a volte può migliorare l'accuratezza e le sfumature, soprattutto per le query complesse.

I passaggi di ragionamento sono inclusi come parte della risposta. Per analizzare i passaggi di ragionamento a partire dalla risposta che stai cercando, puoi specificare un formato di output utilizzando XML o altri separatori.

Esempi

Ad esempio, supponiamo che tu stia scrivendo un blog di cucina e che tu voglia che il modello ti indichi come i lettori potrebbero interpretare le diverse parti del blog. Se non chiedi al modello di spiegare il suo ragionamento, la risposta del modello potrebbe non essere così utile come vorresti:

Nessun ragionamento
    What is the most likely interpretation of this sentence?
    
    The sentence: "The chef seasoned the chicken and put it in the oven because it looked pale."
    
    The chef seasoned the chicken and put it in the oven because it lacked color and needed cooking.
    

Anche se hai appreso come il modello prevede che i lettori potrebbero interpretare la frase, potrebbe essere utile per comprendere meglio le previsioni specifiche effettuate dal modello per produrre la risposta. Come dimostrato nell'esempio seguente, anche la qualità della risposta potrebbe migliorare:

Spiega il ragionamento
    What is the most likely interpretation of this sentence? Explain your reasoning
    
    The sentence: "The chef seasoned the chicken and put it in the oven because it looked pale."
    
      Interpreting "The chef seasoned the chicken and put it in the oven because it looked pale."

      The most likely interpretation is that the chef seasoned the chicken to add flavor and color, then put it in the oven to cook it.

      Here's the reasoning:

      - Seasoning is typically used to enhance the flavor of food. Chefs often use spices, herbs, and other ingredients to make their dishes more appealing.
      - "Pale" suggests the chicken lacked visual appeal before being seasoned. This could imply it was unseasoned or simply lacking color from spices.
      - Putting the chicken in the oven is a common cooking method. The sentence implies the chef's intention is to cook the chicken, not just season it.

      Therefore, the chef's actions are likely aimed at both improving the taste and appearance of the chicken through seasoning and then cooking it in the oven.
    

Un'altra tecnica che puoi utilizzare per migliorare la risposta del modello è istruire il modello a pensare passo passo e spiegare il suo ragionamento. Il modello deve scomporre l'input in passaggi e fornire il ragionamento da utilizzare per risolvere il problema:

Segui le istruzioni passo passo
    What is the most likely interpretation of this sentence? Think step by step and print out
    the thinking process.

    Please output in JSON format with final answer in 'answer', and thinking steps in 'think' fields.
    
    The sentence: "The chef seasoned the chicken and put it in the oven because it looked pale."
    
    {
      "answer": "The chef seasoned the chicken to enhance its flavor and put it in the oven to cook it because it appeared to be undercooked.",
      "think": [
        {
          "step": 1,
          "thought": "The chef seasoned the chicken. This suggests that the chef is preparing the chicken for cooking."
        },
        {
          "step": 2,
          "thought": "The chef put the chicken in the oven. This indicates that the chef is cooking the chicken."
        },
        {
          "step": 3,
          "thought": "The sentence states that the chicken looked pale. Pale chicken is often undercooked."
        },
        {
          "step": 4,
          "thought": "Combining these observations, it is most likely that the chef seasoned the chicken to enhance its flavor and put it in the oven to cook it because it appeared to be undercooked."
        }
      ]
    }
    

Chiedendo al modello di stampare il suo processo di pensiero, il modello ha generato una risposta più approfondita e hai appreso di più su come ha generato questa risposta.

Passaggi successivi