Modifying LLM Responses for Desired Formats

Welcome to this lesson on adjusting LLM's messages. Today, we will focus on refining LLM responses to achieve more accurate and useful outputs. By learning how to modify LLM messages, you can enhance the quality of interactions and ensure that the responses meet your specific needs.

To guide LLMs in producing structured responses, it is crucial to define the desired answer format. This involves specifying constraints that the LLM should follow. For example, if you want a list of teaching strategies, you should clearly state that in your prompt. This helps the LLM understand the structure you expect in its response.

Consider the following prompt:

Provide me with a list of teaching strategies for engaging middle school students. Include overview.

By specifying that you want a "list" and an "overview," you are setting clear expectations for the LLM's response format. However, this is not specific enough. Let's consider a sample output of LLM:

Certainly! Engaging middle school students requires strategies that address their developmental needs and interests. Here's a list of effective teaching strategies for middle school students:

### Active Learning Strategies

1. **Project-Based Learning**
   - **Overview**: Project-based learning involves students working on complex projects that address real-world problems. It encourages critical thinking, collaboration, and creativity.
   - **Implementation**: Start with a driving question, provide structured milestones, and culminate with student presentations of their work.

2. **Cooperative Learning**
   - **Overview**: Cooperative learning involves students working together in small groups to maximize their own and each other's learning.
   - **Implementation**: Assign specific roles to group members, establish clear objectives, and provide opportunities for group reflection.

...

### Technology Integration Strategies

1. **Digital Storytelling**
   - **Overview**: Digital storytelling combines narrative with digital content to create engaging multimedia presentations.
   - **Implementation**: Have students create digital stories using tools like PowerPoint, Google Slides, or specialized apps.

...

### Assessment Strategies

...

A part of the output is omitted for clarity. This output is not what we expected: it includes implementation details we didn't ask for. Also, we only want to see active learning strategies.

One approach is to introduce a constraints section with many specific instructions. Let's take a look at a more efficient approach.

Let's consider a dialogue where the LLM's response doesn't match what we want. You can modify your message by hovering over it and clicking the edit button that appears:

This opens an edit field where you can change the text of your message. Modern chat-based LLM works as follows: it takes the whole previous dialogue and predicts the following reply. This means that even slight modifications to previous responses can significantly impact subsequent outputs. If an LLM's response includes unnecessary details, restructuring the answer before continuing the dialogue ensures that future responses adhere more closely to the desired format. However, one potential limitation is that changes made to the response do not "erase" the model's original reasoning—they only shift its interpretation for future responses. If inconsistencies persist, resetting the conversation might be necessary.

Once you have modified the message, click Save:

Let's test if LLM treats the new version of the message as the original and responds accordingly:

Great!

When the initial response from an LLM doesn't fully meet your expectations, you can manually adjust the response to better fit the desired format. This process improves the clarity of the response and helps the LLM understand the task more effectively. When you ask the next question, LLM will treat the modified answer as its initial answer and is likely to answer using the same format.

For instance, let's reorganize the LLM's answer in the following way:

### Active Learning Strategies

1. **Project-Based Learning**

Project-based learning involves students working on complex projects that address real-world problems. It encourages critical thinking, collaboration, and creativity.

2. **Cooperative Learning**

Cooperative learning involves students working together in small groups to maximize their own and each other's learning.

By removing initial context, implementation details, and other strategy types, we implicitly communicate the desired structure to the LLM.

Now, let's ask the following question in the same dialogue. For instance, we can run this prompt:

Good. Now, provide me with strategies for classroom management

And here is the LLM`s answer:

### Classroom Management Strategies

1. **Establish Clear Expectations**
Clearly communicate classroom rules, procedures, and expectations at the beginning of the school year. Consistently reinforce these expectations throughout the year to create a structured learning environment.

2. **Positive Reinforcement**
Acknowledge and reward positive behaviors to encourage students to continue making good choices. This can include verbal praise, recognition systems, or small privileges.

...

Note how LLM answers in the desired format without specifying any additional constraints. By continuing the dialogue and refining the LLM's output, you can guide the LLM to better meet your needs.

Note: this approach can't guarantee the correct format. But it is usually faster than explicitly writing down all the constraints so that it can be very efficient, especially for lesson planning and resource creation. We will see more of such examples in the practice session.

In this lesson, we covered the importance of defining the desired answer format and how to modify LLM responses for clarity. We also explored how continued dialogue can implicitly communicate constraints to the LLM. By practicing these techniques, you can enhance the quality of interactions with LLMs for your teaching needs.

As you move on to the practice exercises, remember that hands-on experience is key to mastering prompt engineering. Use the skills you've learned to refine LLM responses and achieve the desired outcomes for your classroom. Good luck!