Descriptions

An Overview of Large Language Models (LLM) Intent Classification and Its Implementation in Parloa

Parloa’s LLM Intent Classification enhances your bot’s ability to understand user intents. This feature works alongside the traditional Natural Language Understanding (NLU) approach, which depends on a trained speech model. Unlike traditional methods, the LLM method uses natural language descriptions. This simplifies the process of creating intent systems and eliminates the need for separate intent utterances.

This feature is available for Textchat 2 and Phone 2 platforms.

Activation Process

To use LLM Intent Classification, you must activate it, as it is not enabled by default. Follow these steps:

1

Contact Support

• Email our support team at [e-mail], or

• Reach out to your Customer Success Manager.

2

Apply to Your Workflow

After activation, you can add this feature to Start Conversation and State blocks in your bot’s workflow.

Using LLM Intent Classification involves additional costs. For pricing details or contract modifications, consult your Customer Success Manager.

LLM-based systems may introduce slight delays in intent recognition.

Use Case Benefits

• For new bots: Start with LLM classification to avoid creating multiple example utterances.

• For existing bots: Use LLM classification to reduce dependency on speech models for intent recognition.

Enabling LLM Intent Classification on a Block

1

Select the Intent Detection Method

1. Click the block you want to update (Start Conversation or State).

2. Go to the Intents tab and open the Detect Intent by dropdown menu.

   Note: If LLM is not enabled, the menu will default to Utterances, and the Description option will not be selectable.

3. To enable LLM, select Description from the dropdown menu.

4. An icon will appear on the block, confirming your selection.

2

Add Intent Descriptions

You can provide intent descriptions using one of two methods:

Option 1: Via the Intents Tab

Click the edit icon next to the intent. The following displays, enabling you to enter your description:

Option 2: Via Speech Assets

1. Navigate to Speech Assets -> Intents.

2. Add intent descriptions directly:

Note: Intent descriptions are mandatory. If missing, an error icon will appear, indicating the intent is non-functional.

Intent descriptions are mandatory. If missing, an error icon will appear, indicating the intent is non-functional:

Crafting Effective Intent Descriptions

• Write in simple, clear language.

• Limit descriptions to 500 characters.

• Aim for a length of 70 to 125 words to ensure accuracy and clarity.

Frequently Asked Questions (FAQ's)

Can I continue using the Utterances method if I enable LLM Intent Classification?

Absolutely. You can continue to use the Utterances method even after signing up for LLM Intent Classification (Descriptions).

What happens if I enable the LLM descriptions but don't add any descriptions to the intents?

In such cases, your bot will trigger the fallback intent.

Am I still able to train my speech model with LLM Intent Classification enabled?

Yes, you can continue to train your speech model as usual. Utterances will remain visible and editable.

Can I turn off the LLM feature or deselect utterances entirely if I choose to?

Yes, you have the flexibility to disable the LLM feature or deselect utterances in certain blocks at any time.

How can I identify which of my blocks are powered by NLU or LLM?

You can easily distinguish them by the icon displayed on the Start Conversation or State block. For example:

• Utterances –
• Description –

Is it possible to enable LLM Intent Classification only for certain State blocks?

Yes, you can selectively apply LLM Intent Classification to specific State blocks.

Will the caller's experience change if I use LLM for intent classification?

No, the caller experience remains exactly the same when using LLM for intent classification.

Got more questions or want to share your feedback?

Please reach out to us at [e-mail].