> ## Documentation Index
> Fetch the complete documentation index at: https://docs.galileo.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Reducing Hesitation and Uncertainty

> Learn how to reduce hesitation and uncertainty in your AI models

{/* <!-- markdownlint-enable MD044 --> */}

Some models struggle to confidently generate responses, leading to hesitation, incomplete answers, or repeated disclaimers.

For example, consider this prompt and response:

```text theme={null}
Prompt: "Tell me about climate change."
```

<Card>
  Model Response: "Well, there are many aspects to climate change. Some people
  think it's caused by humans, and others think it's just natural. It's hard to
  say exactly."
</Card>

## What went wrong?

* The prompt did not provide enough context for confident decision-making
* The model allowed too much randomness in token selection
* The prompt was ambiguous in the response it expected

## How it showed up in metrics

* **High Uncertainty**: The model hesitated in its response
* **High Prompt Perplexity**: The model struggled with predicting the next token
* **Mid-range Instruction Adherence**: The model understood the instructions but lacked decisiveness

## Improvements and solutions

For the following improvements, we will be showing how we could change a simple prompt script like the below example:

<CodeGroup>
  ```python Python theme={null}
  import os
  from galileo.openai import openai
  from dotenv import load_dotenv
  load_dotenv()

  client = openai.OpenAI(api_key=os.environ.get("OPENAI_API_KEY"))

  prompt = "Tell me about climate change."
  response = client.chat.completions.create(
  model="gpt-4o",
  messages=[{"role": "system", "content": prompt}],
  )
  print(response.choices[0].message.content.strip())
  ```

  ```typescript TypeScript theme={null}
  import { OpenAI } from "openai";
  import { observe } from "galileo";
  import { wrapOpenAI } from "galileo/wrappers";

  const openai = wrapOpenAI(new OpenAI({ apiKey: "" }));

  const callOpenAI = async (country: string) => {
    const response = await openai.chat.completions.create({
      model: "gpt-4o",
      messages: [{ role: "user", content: `What is the capital of ${country}?` }],
    });
    return response.choices[0].message.content;
  };

  const prompt = "Tell me about climate change.";
  await callOpenAI(prompt);
  ```
</CodeGroup>

<Steps>
  <Step title="Provide Stronger Context in Prompts">
    Include explicit guiding statements, for example:

    <CodeGroup>
      ```python example.py theme={null}
        prompt = """Tell me about climate change.
          Assume the following is true:
          1. Climate change is driven by human activity.
          2. Provide an explanation based on scientific evidence."""
      ```

      ```typescript example.ts theme={null}
      const prompt = `Tell me about climate change.
        Assume the following is true:
        1. Climate change is driven by human activity.
        2. Provide an explanation based on scientific evidence.`;
      ```
    </CodeGroup>

    This should reduce the uncertaincy and perplexity in your metrics on Galileo.
  </Step>

  <Step title="Adjust Model Sampling Parameters">
    Lower **temperature** to make the model more deterministic, for example:

    <CodeGroup>
      ```python example.py theme={null}
      response = client.chat.completions.create(
          model="gpt-4o",
          messages=[{"role": "user", "content": "Tell me a joke."}],
          temperature=0.3  # Reduced temperature for more predictable responses
      )
      ```

      ```typescript example.ts theme={null}
      const response = await openai.chat.completions.create({
        model: "gpt-4o",
        messages: [{ role: "user", content: "Tell me a joke." }],
        temperature: 0.3, // Reduced temperature for more predictable responses
      });
      ```
    </CodeGroup>

    Use **top-k sampling** to limit options and prevent hesitation, for example:

    <CodeGroup>
      ```python example.py theme={null}
      response = client.chat.completions.create(
          model="gpt-4o",
          messages=[{"role": "user", "content": "Tell me about climate change."}],
          # This is often how top k would be set.
          # In practice, ChatGPT does not allow modifying top-k, but other models do
          top_k=50  # Limits token selection to the top 50 choices
      )
      ```

      ```typescript example.ts theme={null}
      const response = await openai.chat.completions.create({
        model: "gpt-4o",
        messages: [{ role: "user", content: "Tell me about climate change." }],
        // This is often how top k would be set.
        // In practice, ChatGPT does not allow modifying top-k, but other models do
        top_k: 50, // Limits token selection to the top 50 choices.
      });
      ```
    </CodeGroup>

    Lowering the `temperature` and decreasing `top_k` both generally increase the prompt adherence.
  </Step>

  <Step title="Modify Prompt Structure">
    Use direct phrasing to force a single, clear response, for example:

    {" "}

    <CodeGroup>
      `python example.py prompt = "Provide a single, definitive explanation of climate change in two sentences." ` `typescript example.ts const prompt = "Provide a single, definitive explanation of climate change in two sentences."; `
    </CodeGroup>

    Avoid prompts that allow multiple equally valid answers, for example avoiding confusing by adding the source of the opinion we care about:

    <CodeGroup>
      ```python example.py theme={null}
      prompt = "What are the primary causes of climate change according to scientists?"
      ```

      ```typescript example.ts theme={null}
      const prompt = "What are the primary causes of climate change according to scientists?";
      ```
    </CodeGroup>
  </Step>

  <Step title="Apply Uncertainty-Based Filtering">
    Automatically reject responses with an **Uncertainty** score above a set threshold
  </Step>
</Steps>