Ways to Use ChatGPT for Customer Service

Now that we’ve all seen what ChatGPT can do, it’s natural to begin casting about for ways to put it to work. An obvious place where a generative AI language model can be used is in contact centers, which involve a great deal of text-based tasks like answering customer questions and resolving their issues.

But is ChatGPT ready for the on-the-ground realities of contact centers? What if it responds inappropriately, abuses a customer, or provides inaccurate information?

We at Quiq pride ourselves on being experts in the domain of customer experience and customer service, and we’ve been watching the recent developments in the realm of generative AI for some time. This piece presents our conclusions about what ChatGPT is, the ways in which ChatGPT can be used for customer service, and the techniques that exist to optimize it for this domain.

What is ChatGPT?

ChatGPT is an application built on top of GPT-4, a large language model. Large language models like GTP-4 are trained on huge amounts of textual data, and they gradually learn the statistical patterns present in that data well enough to output their own, new text.

How does this training work? Well, when you hear a sentence like “I’m going to the store to pick up some _____”, you know that the final word is something like “milk”, “bread”, or “groceries”, and probably not “sawdust” or “livestock”. This is because you’ve been using English for a long time, you’re familiar with what happens at a grocery store, and you have a sense of how a person is likely to describe their exciting adventures there (nothing gets our motor running like picking out the really good avocados).

GPT-4, of course, has none of this context, but if you show it enough examples it can learn to imitate natural language quite well. It will see the first few sentences of a paragraph and try to predict what the final sentence is. At first, its answers are terrible, but with each training run its internal parameters are updated, and it gradually gets better. If you do this for long enough you get something that can write its own emails, blog posts, research reports, book summaries, poems, and codebases.

Is ChatGPT the Same Thing as GPT-4?

So then, how is ChatGPT different from GPT-4? GPT-4 is the large language model trained in the manner just described, and ChatGPT is a version fine-tuned using reinforcement learning with human feedback to be good at conversations.

Fine-tuning refers to a process of taking a pre-trained language model and doing a little extra work to narrow its focus to doing a particular task. A generic LLM can do many things, including write limericks; but if you want it to consistently write high-quality limericks, you’ll need to fine-tune it by showing it a few dozen or a few hundred examples of them.

From that point on it will be specialized for limerick production, and might consequently be less useful for other tasks.

This is how ChatGPT was created. After GPT-3.5 or GPT-4 was finished training, engineers did additional fine-tuning work that led to a model that was especially good at having open-ended interactions with users.

What does ChatGPT mean for Customer Service?

Given that ChatGPT is useful for customer interactions, how might it be deployed in customer service? We believe that a good list of initial use cases includes question answering, personalizing responses to different customers, summarizing important information, translating between languages, and performing sentiment analysis.

This is certainly not everything current and future versions of ChatGPT will be able to do for customer service, but we think it’s a good place to start.

Question Answering

Question answering has long been of such interest to machine learning engineers that there’s a whole bespoke dataset specifically for it (the Stanford Question Answering Dataset, or SQuAD).

It’s not hard to see why. Humans can obviously answer questions, but there are so many possible questions that there’s just no way to get to it all. What if you’d like high-level summaries of all the major research papers published about an obscure scientific sub-discipline? What if you’d like to see how the tone of Victorian-era English novels changed over time? There are only so many person-hours that can go toward digging into queries like this.

Customers, too, have many questions, and answering them takes a lot of time. You could collect all the frequently asked questions and put them into a single document for easy reference, but there are still going to be areas of confusion and requests for clarification (and that’s not even considering the fraction of users who never make it to your FAQ page in the first place).

Automating the process of asking questions is an obvious place to utilize technology like ChatGPT. It’ll never get frustrated answering the same thing thousands of times, it’ll never lose its patience, it’ll never sleep, and it’ll never take a bathroom break.

Vanilla ChatGPT is pretty good at doing this already, and there are already many projects focused on getting it to answer questions about a particular company’s documentation.

This functionality will enable you to field an effectively unlimited number of customer questions while freeing up your contact center agents to tackle more important issues.

Onboarding New Hires

Customers are not the only people who might have questions about your product – new hires unfamiliar with your process for doing things might also have their fair share of confusion.

Even in companies that are very conscious about documentation, there can often be so much to get through that new employees – who already have a lot going on – can feel overwhelmed.

A large language model trained to answer questions about your documentation will be a godsend to the fresh troops you’ve brought in.


A related task is summarizing email threads, important technical documents, or even videos.

Just as you can’t realistically expect every customer to assiduously look through all your company’s documents, it’s usually not realistic to expect that all of your own employees will do so either.

Here, too, is a place where ChatGPT can be useful. It’s quite good at taking a lengthy bit of text and summarizing it, so there’s no reason it can’t be used to keep your teams up to speed on what’s happening in parts of the organization that they don’t interact with all that often.

If your engineers don’t want to go over an exchange between product designers, or your marketing team doesn’t want all the details of a conversation between the data scientists, ChatGPT can be used to create summaries of these interactions for easier reading.

This way everyone knows what’s going on throughout the company without needing to spend hours every day staying abreast of evolving issues.

At Quiq, we’ve developed proprietary ways to harness ChaGPT’s generative abilities to summarize conversations for your contact center agents.

Sentiment Analysis

Finally, another way in which ChatGPT will power the contact center of the future is with sentiment analysis. Sentiment analysis refers to a branch of machine learning aimed at parsing the overall tone of a piece of text. This can be more subtle than you might think.

“I hate this restaurant” is pretty unambiguous, but what about a review like “Yeah, we loved this restaurant, we had plenty of time to chat because the food took an hour to come out, and since my enchilada was frozen it counteracted my usual inability to eat spicy food”? You and I can hear the implied eye-rolling in this text, but a machine won’t necessarily be able to unless it’s very powerful.

This matters for contact centers because you need to understand how people are talking about your product, whether that’s in online reviews, internal tickets, or during conversations with your agents.

And ChatGPT can help. It’s not only quite good at sentiment analysis, but it’s also better than quite a lot of alternative machine-learning approaches to sentiment analysis, even without fine-tuning.

(Note, however, that these tests compare it to relatively simple machine learning models, not to the very best deep-learning sentiment analyzers.)

Prioritizing Incoming Issues

One way that ChatGPT can add tremendous value to your contact center is in helping to prioritize issues as they come in. There are always lots of problems to solve, but they’re not all equally important. Finding the most pressing issues and marking them for resolution is a huge part of keeping your center running smoothly.

This is something that humans can do, but there’s only so much energy they can devote to this task. A properly trained generative language model, however, can handle a huge chunk of it, especially when it forms part of a broader suite of AI tools.

One way this could work is using ChatGPT for plucking out essential keywords from a customer service ticket. This by itself might be enough to help your contact center agents figure out what they should focus on, but it can be made even better if these words are then fed to a classification algorithm trained to identify urgent problems.

Real-time Language Translation

Language translation, too, is a clear use case for LLMs, and the deep learning upon which they are based has seen much success in translating from one language to another.

This is especially useful if your product or service enjoys a global audience. Many people have a passing familiarity with English but will not necessarily be able to follow a detailed procedure involving technical vocabulary, and that will be a source of frustration for them.

By substantially or totally automating real-time language translation, ChatGPT can help customers who lack English fluency to better interact with your company’s offerings, answering their questions, resolving their issues, and in general moving them along.

And in case you’re wondering, ChatGPT is currently even better than Google Translate or DeepL at most translation tasks, including tricky ones involving jokes and humor.

Fine-Tuning ChatGPT for Customer Service

So far we’ve mostly talked about ChatGPT out of the box, but we’ve also made some references to “fine-tuning” it.

In this section, we’ll flesh out our earlier comments about fine-tuning ChatGPT, and distinguish fine-tuning from related techniques, like prompt engineering.

What is Fine-Tuning ChatGPT?

Once upon a time, it was anyone’s guess as to whether you’d be able to pre-train a single large model on a dataset and then tweak it for particular applications, or whether you’d need to train a special model for every individual task.

Beginning around 2011, it became increasingly clear that for many applications, pre-training was the way to go, and since then, many techniques have been developed for doing the subsequent fine-tuning.

When you fine-tune a pre-trained generative AI model, you are effectively altering its internal structure so that it does better on the task you’re interested in. Sometimes this involves changing the whole model, other times you’re altering the last few output layers and leaving the rest of the model intact.

But what it ultimately boils down to is creating a fine-tuning pipeline through which your model sees a lot of examples of the behavior you’re trying to elicit. If you were fine-tuning it to be more polite in its follow-up questions, for example, you’d need to collect a bunch of examples of this politeness and have your model learn on them.

How many examples you end up needing will depend on your specific use case, but it’s usually a few dozen and could be as many as a few hundred.

How is Fine-Tuning Different From Prompt Engineering?

Prompt engineering refers to the practice of carefully sculpting the prompt you feed your model to do a better job of producing the output you want to see.

The reason this works is that GPT-4 and other LLMs are extremely sensitive to slight changes in the wording of their prompts. It takes a while to develop the feel required to reliably produce good results with an LLM, and all of this falls under the label of “prompt engineering”.

It’s possible to inject some light fine-tuning into prompt engineering, through one-shot and few-shot learning. One-shot learning means including one example of the behavior you want to see in your prompt, and few-shot learning is the same idea, but you’re including 2-5 examples for the LLM to learn from.

FAQs About ChatGPT for Customer Service

Now that we’ve finished our discussion of the basics of ChatGPT for customer service, we’ll spend some time addressing common questions about this subject.

Can I Use ChatGPT for Customer Service?

Yes! ChatGPT is ideal for customer service applications, but you need to fine-tune ChatGPT on your own company’s documentation or to get it to strike the right tone. With the right guardrails, it’s a powerful tool for those looking to build a forward-looking contact center.

What are the Examples of ChatGPT in Customer Service?

ChatGPT can be used for customer service tasks like question answering, sentiment analysis, translating between natural languages, and summarizing documents. These are all time-intensive tasks, the automation of which will free up your contact center agents to focus on higher-priority work.

Can you Automate Customer Service?

Tools like AutoGPT and SuperAGI are making it easier than ever to create and manage sophisticated agents capable of handling open-ended tasks. Still, artificial intelligence is not yet flexible enough to entirely automate customer service at present.

It can be used to automate substantial parts of customer service, like answering user questions, but for the moment the lion’s share of the work must still be done by flesh-and-blood human beings.

If you’re interested in developments in this space, be sure to follow the Quiq blog for updates.

ChatGPT and the Contact Center of the Future

ChatGPT and related technologies are already changing the way contact centers function. From automated translation to helping field dramatically more questions per hour, they are helping contact center agents be more productive and reducing organizational turnover.

The Quiq platform is an excellent tool for incorporating conversational AI into your offering, without having to hire a team or manage your own infrastructure. Quiq can help you automate text messaging, handle real-time translation, and track the performance of your AI Assistants to see where improvements need to be made.

Exploring Cutting-Edge Research in Large Language Models and Generative AI

By the calendar, ChatGPT was released just a few months ago. But subjectively, it feels as though 600 years have passed since we all read “as a large language model…” for the first time.

The pace of new innovations is staggering, but we at Quiq like to help our audience in the customer experience and contact center industries stay ahead of the curve (even when that requires faster-than-light travel).

Today, we will look at what’s new in generative AI, and what will be coming down the line in the months ahead.

Where will Generative AI be applied?

First, let’s start with industries that will be strongly impacted by generative AI. As we noted in an earlier article, training a large language model (LLM) like ChatGPT mostly boils down to showing it tons of examples of text until it learns a statistical representation of human language well enough to generate sonnets, email copy, and many other linguistic artifacts.

There’s no reason the same basic process (have it learn it from many examples and then create its own) couldn’t be used elsewhere, and in the next few sections, we’re going to look at how generative AI is being used in a variety of different industries to brainstorm structures, new materials, and a billion other things.

Generative AI in Building and Product Design

If you’ve had a chance to play around with DALL-E, Midjourney, or Stable Diffusion, you know that the results can be simply remarkable.

It’s not a far leap to imagine that it might be useful for quickly generating ideas for buildings and products.

The emerging field of AI-generated product design is doing exactly this. With generative image models, designers can use text prompts to rough out ideas and see them brought to life. This allows for faster iteration and quicker turnaround, especially given that creating a proof of concept is one of the slower, more tedious parts of product design.

Image source: Board of Innovation


For the same reason, these tools are finding use among architects who are able to quickly transpose between different periods and styles, see how better lighting impacts a room’s aesthetic, and plan around themes like building with eco-friendly materials.

There are two things worth pointing out about this process. First, there’s often a learning curve because it can take a while to figure out prompt engineering well enough to get a compelling image. Second, there’s a hearty dose of serendipity. Often the resulting image will not be quite what the designer had in mind, but it’ll be different in new and productive ways, pushing the artist along fresh trajectories that might never have occurred to them otherwise.

Generative AI in Discovering New Materials

To quote one of America’s most renowned philosophers (Madonna), we’re living in a material world. Humans have been augmenting their surroundings since we first started chipping flint axes back in the Stone Age; today, the field of materials science continues the long tradition of finding new stuff that expands our capabilities and makes our lives better.

This can take the form of something (relatively) simple like researching a better steel alloy, or something incredibly novel like designing a programmable nanomaterial.

There’s just one issue: it’s really, really difficult to do this. It takes a great deal of time, energy, and effort to even identify plausible new materials, to say nothing of the extensive testing and experimenting that must then follow.

Materials scientists have been using machine learning (ML) in their process for some time, but the recent boom in generative AI is driving renewed interest. There are now a number of projects aimed at e.g. using variational autoencoders, recurrent neural networks, and generative adversarial networks to learn a mapping between information about a material’s underlying structure and its final properties, then using this information to create plausible new materials.

It would be hard to overstate how important the use of generative AI in materials science could be. If you imagine the space of possible molecules as being like its own universe, we’ve explored basically none of it. What new fabrics, medicines, fuels, fertilizers, conductors, insulators, and chemicals are waiting out there? With generative AI, we’ve got a better chance than ever of finding out.

Generative AI in Gaming

Gaming is often an obvious place to use new technology, and that’s true for generative AI as well. The principles of generative design we discussed two sections ago could be used in this context to flesh out worlds, costumes, weapons, and more, but it can also be used to make character interactions more dynamic.

From Navi trying to get our attention in Ocarina of Time to GlaDOS’s continual reminders that “the cake is a lie” in Portal, non-playable characters (NPCs) have always added texture and context to our favorite games.

Powered by LLMs, these characters may soon be able to have open-ended conversations with players, adding more immersive realism to the gameplay. Rather than pulling from a limited set of responses, they’d be able to query LLMs to provide advice, answer questions, and shoot the breeze.

What’s Next in Generative AI?

As impressive as technologies like ChatGPT are, people are already looking for ways to extend their capabilities. Now that we’ve covered some of the major applications of generative AI, let’s look at some of the exciting applications people are building on top of it.

What is AutoGPT and how Does it Work?

ChatGPT can already do things like generate API calls and build simple apps, but as long as a human has to actually copy and paste the code somewhere useful, its capacities are limited.

But what if that weren’t an issue? What if it were possible to spin ChatGPT up into something more like an agent, capable of semi-autonomously interacting with software or online services to complete strings of tasks?

This is exactly what Auto-GPT is intended to accomplish. Auto-GPT is an application built by developer Toran Bruce Richards, and it is comprised of two parts: an LLM (either GPT-3.5 or GPT-4), and a separate “bot” that works with the LLM.

By repeatedly querying the LLM, the bot is able to take a relatively high-level task like “help me set up an online business with a blog and a website” or “find me all the latest research on quantum computing”, decompose it into discrete, achievable steps, then iteratively execute them until the overall objective is achieved.

At present, Auto-GPT remains fairly primitive. Just as ChatGPT can get stuck in repetitive and unhelpful loops, so too can Auto-GPT. Still, it’s a remarkable advance, and it’s spawned a series of other projects attempting to do the same thing in a more consistent way.

The creators of AssistGPT bill it as a “General Multi-modal Assistant that can Plan, Execute, Inspect, and Learn”. It handles multi-modal tasks (i.e. tasks that rely on vision or sound and not just text) better than Auto-GPT, and by integrating with a suite of tools it is able to achieve objectives that involve many intermediate steps and sub-tasks.

SuperAGI, in turn, is just as ambitious. It’s a platform that offers a way to quickly create, deploy, manage, and update autonomous agents. You can integrate them into applications like Slack or vector databases, and it’ll even ping you if an agent gets stuck somewhere and starts looping unproductively.

Finally, there’s LangChain, which is a similar idea. LangChain is a framework that is geared towards making it easier to build on top of LLMs. It features a set of primitives that can be stitched into more robust functionality (not unlike “for” and “while” loops in programming languages), and it’s even possible to build your own version of AutoGPT using LangChain.

What is Chain-of-Thought Prompting and How Does it Work?

In the misty, forgotten past (i.e. 5 months ago), LLMs were famously bad at simple arithmetic. They might be able to construct elegant mathematical proofs, but if you asked them what 7 + 4 is, there was a decent chance they’d get it wrong.

Chain-of-thought (COT) prompting refers to a few-shot learning method of eliciting output from an LLM that compels it to reason in a step-by-step way, and it was developed in part to help with this issue. This image from the original Wei et al. (2022) paper illustrates how:

Input and output examples for Standard and Chain-of-thought Prompting.
Source: ARXIV.org

As you can see, the model’s performance is improved because it’s being shown a chain of different thoughts, hence chain-of-thought.

This technique isn’t just useful for arithmetic, it can be utilized to get better output from a model in a variety of different tasks, including commonsense and symbolic reasoning.

In a way, humans can be prompt engineered in the same fashion. You can often get better answers out of yourself or others through a deliberate attempt to reason slowly, step-by-step, so it’s not a terrible shock that a large model trained on human text would benefit from the same procedure.

The Ecosystem Around Generative AI

Though cutting-edge models are usually the stars of the show, the truth is advanced technologies aren’t worth much if you have to be deeply into the weeds to use them. Machine learning, for example, would surely be much less prevalent if tools like sklearn, Tensorflow, and Keras didn’t exist.

Though we’re still in the early days of LLMs, AutoGPT, and everything else we’ve discussed, we suspect the same basic dynamic will play out. Since it’s now clear that these models aren’t toys, people will begin building infrastructure around them that streamlines the process of training them for specific use cases, integrating them into existing applications, etc.

Let’s discuss a few efforts in this direction that are already underway.

Training and Education

Among the simplest parts of the emerging generative AI value chain is exactly what we’re doing now: talking about it in an informed way. Non-specialists will often lack the time, context, and patience required to sort the real breakthroughs from the hype, so putting together blog posts, tutorials, and reports that make this easier is a real service.

Making Foundation Models Available

“Foundation models” is a new term that refers to the actual algorithms that underlie LLMs. ChatGPT, for example, is not a foundation model. GPT-4 is the foundation model, and ChatGPT is a specialized application of it (more on this shortly).

Companies like Anthropic, Google, and OpenAI can train these gargantuan models and then make them available through an API. From there, developers are able to access their preferred foundation model over an API.

This means that we can move quickly to utilize their remarkable functionality, which wouldn’t be the case if every company had to train their own from scratch.

Building Applications Around Specific Use Cases

One of the most striking properties of ChatGPT is how amazingly general they are. They are capable of “…generating functioning web apps with just a few prompts, writing Spanish-language children’s stories about the blockchain in the style of Dr. Suess, [and] opining on the virtues and vices of major political figures”, to name but a few examples.

General-purpose models often have to be fine-tuned to perform better on a specific task, especially if they’re doing something tricky like summarizing medical documents with lots of obscure vocabulary. Alas, there is a tradeoff here, because in most cases these fine-tuned models will afterward not be as useful for generic tasks.

The issue, however, is that you need a fair bit of technical skill to set up a fine-tuning pipeline, and you need a fair bit of elbow grease to assemble the few hundred examples a model needs in order to be fine-tuned. Though this is much simpler than training a model in the first place it is still far from trivial, and we expect that there will soon be services aimed at making it much more straightforward.

LLMOps and Model Hubs

We’d venture to guess you’ve heard of machine learning, but you might not be familiar with the term “MLOps”. “Ops” means “operations”, and it refers to all the things you have to do to use a machine learning model besides just training it. Once a model has been trained it has to be monitored, for example, because sometimes its performance will begin to inexplicably degrade.

The same will be true of LLMs. You’ll need to make sure that the chatbot you’ve deployed hasn’t begun abusing customers and damaging your brand, or that the deep learning tool you’re using to explore new materials hasn’t begun to spit out gibberish.

Another phenomenon from machine learning we think will be echoed in LLMs is the existence of “model hubs”, which are places where you can find pre-trained or fine-tuned models to use. There certainly are carefully guarded secrets among technologists, but on the whole, we’re a community that believes in sharing. The same ethos that powers the open-source movement will be found among the teams building LLMs, and indeed there are already open-sourced alternatives to ChatGPT that are highly performant.

Looking Ahead

As they’re so fond of saying on Twitter, “ChatGPT is just the tip of the iceberg.” It’s already begun transforming contact centers, boosting productivity among lower-skilled workers while reducing employee turnover, but research into even better tools is screaming ahead.

Frankly, it can be enough to make your head spin. If LLMs and generative AI are things you want to incorporate into your own product offering, you can skip the heady technical stuff and skip straight to letting Quiq do it for you. The Quiq conversational AI platform is a best-in-class product suite that makes it much easier to utilize these technologies. Schedule a demo to see how we can help you get in on the AI revolution.

How to Evaluate Generated Text and Model Performance

Machine learning is an incredibly powerful technology. That’s why it’s being used in everything from autonomous vehicles to medical diagnoses to the sophisticated, dynamic AI Assistants that are handling customer interactions in modern contact centers.

But for all this, it isn’t magic. The engineers who build these systems must know a great deal about how to evaluate them. How do you know when a model is performing as expected, or when it has begun to overfit the data? How can you tell when one model is better than another?

This subject will be our focus today. We’ll cover the basics of evaluating a machine learning model with metrics like mean squared error and accuracy, then turn our attention to the more specialized task of evaluating the generated text of a large language model like ChatGPT.

How to Measure the Performance of a Machine Learning Model?

A machine learning model is always aimed at some task. It might be trying to fit a regression line that helps predict the future price of Bitcoin, it might be clustering documents according to their topics, or it might be trying to generate text so good it rivals that produced by humans.

How does the model know when it’s gotten the optimal line or discovered the best way to cluster documents? (And more importantly, how do you know?)

In the next few sections, we’ll talk about a few common ways of evaluating the performance of a machine-learning model. If you’re an engineer this will help you create better models yourself, and if you’re a layperson, it’ll help you better understand how the machine-learning pipeline works.

Evaluation Metrics for Regression Models

Regression is one of the two big types of basic machine learning, with the other being classification.

In tech-speak, we say that the purpose of a regression model is to learn a function that maps a set of input features to a real value (where “real” just means “real numbers”). This is not as scary as it sounds; you might try to create a regression model that predicts the number of sales you can expect given that you’ve spent a certain amount on advertising, or you might try to predict how long a person will live on the basis of their daily exercise, water intake, and diet.

In each case, you’ve got a set of input features (advertising spend or daily habits), and you’re trying to predict a target variable (sales, life expectancy).

The relationship between the two is captured by a model, and a model’s quality is evaluated with a metric. Popular metrics for regression models include the mean squared error, the root mean squared error, and the mean absolute error (though there are plenty of others if you feel like going down a nerdy rabbit hole).

The mean squared error (MSE) quantifies how good a regression model is by calculating the difference between the line and each real data point, squaring them (so that positive and negative differences don’t cancel out), and then averaging them. This gives a single number that the training algorithm can use to adjust its model – if the MSE is going down, the model is getting better, if it’s going up, it’s getting worse.

The root mean squared error (RMSE) does the exact same thing, but the final step is that you take the square root of the MSE. The big advantage here is that it converts the units of your metric back into the units you’re using in your problem (i.e. the “squared dollars” of MSE become “dollars” again, which makes it easier to think about what’s going on).

The mean absolute error (MAE) is the same basic idea, but it uses absolute values instead of squares. This also has the advantage of not penalizing outliers as much as the RMSE does. If you’ve got some outlier data point that’s far away from your model, squaring the difference will result in a bigger error than simply taking the absolute value of that difference. For this reason, it’s less sensitive to outliers in the dataset.

Evaluation Metrics for Classification Models

People tend to struggle less with understanding classification models because it’s more intuitive: you’re building something that can take a data point (the price of an item) and sort it into one of a number of different categories (i.e. “cheap”, “somewhat expensive”, “expensive”, “very expensive”).

Of course, the categories you choose will depend on the problem you’re trying to solve and the domain you’re operating in – a $100 apple is certainly “very expensive”, but a $100 dollar wedding ring…will probably get you left at the altar.

Regardless, it’s just as essential to evaluate the performance of a classification model as it is to evaluate the performance of a regression model. Some common evaluation metrics for classification models are accuracy, precision, and recall.

Accuracy is simple, and it’s exactly what it sounds like. You find the accuracy of a classification model by dividing the number of correct predictions it made by the total number of predictions it made altogether. If your classification model made 1,000 predictions and got 941 of them right, that’s an accuracy rate of 94.1% (not bad!)

Both precision and recall are subtler variants of this same idea. The precision is the number of true positives (correct classifications) divided by the sum of true positives and false positives (incorrect positive classifications). It says, in effect, “When your model thought it had identified a needle in a haystack, this is how often it was correct.”

The recall is the number of true positives divided by the sum of true positives and false negatives (incorrect negative classifications). It says, in effect “There were 200 needles in this haystack, and your model found 72% of them.”

Accuracy tells you how well your model performed overall, precision tells you how confident you can be in its positive classifications, and recall tells you how often it found the positive classifications.

(You may be wondering if this isn’t overkill. Do we really need all these different ratios? Answering that question fully would take us too far from our purpose of measuring the quality of text from generative AI models, but suffice it to say that there are trade-offs involved. Sometimes it makes more sense to focus on boosting the precision, other times getting a higher recall is more important. These are all just different tools for figuring out how to spend your limited time and energy to get a model that best solves your problem.)

Contact Us

How Can I Assess the Performance of a Generative AI Model?

Now, we arrive at the center of this article. Everything up to now has been background context that hopefully has given you a feel for how models are evaluated, because from here on out it’s a bit more abstract.

Using Reference Text for Evaluating Generative Models

When we wanted to evaluate a regression model, we started by looking at how far its predictions were from actual data points.

Well, we do essentially the same thing with generative language models. To assess the quality of text generated by a model, we’ll compare it against high-quality text that’s been selected by domain experts.

The Bilingual Evaluation Understudy (BLEU) Score

The BLEU score can be used to actually quantify the distance between the generated and reference text. It does this by comparing the amount of overlap in the n-grams [1] between the two using a series of weighted precision scores.

The BLEU score varies from 0 to 1. A score of “0” indicates that there is no n-gram overlap between the generated and reference text, and the model’s output is considered to be of low quality. A score of “1”, conversely, indicates that there is total overlap between the generated and reference text, and the model’s output is considered to be of high quality.

Comparing BLEU scores across different sets of reference texts or different natural languages is so tricky that it’s considered best to avoid it altogether.

Also, be aware that the BLEU score contains a “brevity penalty” which discourages the model from being too concise. If the model’s output is too much shorter than the reference text, this counts as a strike against it.

The Recall-Oriented Understudy for Gisting Evaluation (ROGUE) Score

Like the BLEU score, the ROGUE score is examining the n-gram overlap between an output text and a reference text. Unlike the BLEU score, however, it uses recall instead of precision.

There are three types of ROGUE scores:

  1. rogue-n: Rogue-n is the most common type of ROGUE score, and it simply looks at n-gram overlap, as described above.
  2. rogue-l: Rogue-l looks at the “Longest Common Subsequence” (LCS), or the longest chain of tokens that the reference and output text share. The longer the LCS, of course, the more the two have in common.
  3. rogue-s: This is the least commonly-used variant of the ROGUE score, but it’s worth hearing about. Rogue-s concentrates on the “skip-grams” [2] that the two texts have in common. Rogue-s would count “He bought the house” and “He bought the blue house” as overlapping because they have the same words in the same order, despite the fact that the second sentence does have an additional adjective.

The Metric for Evaluation of Translation with Explicit Ordering (METEOR) Score

The METEOR Score takes the harmonic mean of the precision and recall scores for 1-gram overlap between the output and reference text. It puts more weight on recall than on precision, and it’s intended to address some of the deficiencies of the BLEU and ROGUE scores while maintaining a pretty close match to how expert humans assess the quality of model-generated output.

BERT Score

At this point, it may have occurred to you to wonder whether the BLEU and ROGUE scores are actually doing a good job of evaluating the performance of a generative language model. They look at exact n-gram overlaps, and most of the time, we don’t really care that the model’s output is exactly the same as the reference text – it needs to be at least as good, without having to be the same.

The BERT score is meant to address this concern through contextual embeddings. By looking at the embeddings behind the sentences and comparing those, the BERT score is able to see that “He quickly ate the treats” and “He rapidly consumed the goodies” are expressing basically the same idea, while both the BLEU and ROGUE scores would completely miss this.

Final thoughts.

We’ve all seen what generative AI can do, and it’s fair at this point to assume this technology is going to become more prevalent in fields like software engineering, customer service, customer experience, and marketing.

But, as magical as generative AI might seem to be, they’re just models. They have to be evaluated and monitored just like any other, or you risk having a bad one negatively impact your brand.

If you’re enchanted by the potential of using generative algorithms in your contact center but are daunted by the challenge of putting together an engineering team, reach out to us for a demo of the Quiq conversational CX platform. We can help you put this cutting-edge technology to work without having to worry about all the finer details and resourcing issues.



[1] An n-gram is just a sequence of characters, words, or entire sentences. A 1-gram is usually single words, a 2-gram is usually two words, etc.
[2] Skip-grams are a rather involved subdomain of natural language processing. You can read more about them in this article, but frankly, most of it is irrelevant to this article. All you need to know is that the rogue-s score is set up to be less concerned with exact n-gram overlaps than the alternatives.

How to Get the Most out of Your NLP Models with Preprocessing

Along with computer vision, natural language processing (NLP) is one of the great triumphs of modern machine learning. While ChatGPT is all the rage and large language models (LLMs) are drawing everyone’s attention, that doesn’t mean that the rest of the NLP field just goes away.

NLP endeavors to apply computation to human-generated language, whether that be the spoken word or text existing in places like Wikipedia. There are any number of ways in which this would be relevant to customer experience and service leaders, including:

Today, we’re going to briefly touch on what NLP is, but we’ll spend the bulk of our time discussing how textual training data can be preprocessed to get the most out of an NLP system. There are a few branches of NLP, like speech synthesis and text-to-speech, which we’ll be omitting.

Armed with this context, you’ll be better prepared to evaluate using NLP in your business (though if you’re building customer-facing chatbots, you can also let the Quiq platform do the heavy lifting for you).

What is Natural Language Processing?

In the past, we’ve jokingly referred to NLP as “doing computer stuff with words after you’ve tricked them into being math.” This is meant to be humorous, but it does capture the basic essence.

Remember, your computer doesn’t know what words are, all it does is move 1’s and 0’s around. A crucial step in most NLP applications, therefore, is creating a numerical representation out of the words in your training corpus.

There are many ways of doing this, but today a popular method is using word vector embeddings. Also known simply as “embeddings”, these are vectors of real numbers. They come from a neural network or a statistical algorithm like word2vec and stand in for particular words.

The technical details of this process don’t concern us in this post, what’s important is that you end up with vectors that capture a remarkable amount of semantic information. Words with similar meanings also have similar vectors, for example, so you can do things like find synonyms for a word by finding vectors that are mathematically close to it.

These embeddings are the basic data structures used across most of NLP. They power sentiment analysis, topic modeling, and many other applications.

For most projects it’s enough to use pre-existing word vector embeddings without going through the trouble of generating them yourself.

Are Large Language Models Natural Language Processing?

Large language models (LLMs) are a subset of natural language processing. Training an LLM draws on many of the same techniques and best practices as the rest of NLP, but NLP also addresses a wide variety of other language-based tasks.

Conversational AI is a great case in point. One way of building a conversational agent is by hooking your application up to an LLM like ChatGPT, but you can also do it with a rules-based approach, through grounded learning, or with an ensemble that weaves together several methods.

Getting the Most out of Your NLP Models with Preprocessing

Data Preprocessing for NLP

If you’ve ever sent a well-meaning text that was misinterpreted, you know that language is messy. For this reason, NLP places special demands on the data engineers and data scientists who must transform text in various ways before machine learning algorithms can be trained on it.

In the next few sections, we’ll offer a fairly comprehensive overview of data preprocessing for NLP. This will not cover everything you might encounter in the course of preparing data for your NLP application, but it should be more than enough to get started.

Why is Data Preprocessing Important?

They say that data is the new oil, and just as you can’t put oil directly in your gas tank and expect your car to run, you can’t plow a bunch of garbled, poorly-formatted language data into your algorithms and expect magic to come out the other side.

But what, precisely, counts as preprocessing will depend on your goals. You might choose to omit or include emojis, for example, depending on whether you’re training a model to summarize academic papers or write tweets for you.

That having been said, there are certain steps you can almost always expect to take, including standardizing the case of your language data, removing punctuation, white spaces and stop words, segmenting and tokenizing, etc.

We treat each of these common techniques below.

Segmentation and Tokenization

An NLP model is always trained on some consistent chunk of the full data. When ChatGPT was trained, for example, they didn’t put the entire internet in a big truck and back it up to a server farm, they used self-supervised learning.

Simplifying greatly, this means that the underlying algorithm would take, say, the first few three sentences of a paragraph and then try to predict the remaining sentence on the basis of the text that came before. Over time it sees enough language to guess that “to be or not to be, that is ___ ________” ends with “the question.”

But how was ChatGPT shown the first three sentences? How does that process even work?

A big part of the answer is segmentation and tokenization.

With segmentation, we’re breaking a full corpus of training text – which might contain hundreds of books and millions of words – down into units like words or sentences.

This is far from trivial. In English, sentences end with a period, but words like “Mr.” and “etc.” also contain them. It can be a real challenge to divide text into sentences without also breaking “Mr. Smith is cooking the steak.” into “Mr.” and “Smith is cooking the steak.”

Tokenization is a related process of breaking a corpus down into tokens. Tokens are sometimes described as words, but in truth they can be words, short clusters of a few words, sub-words, or even individual characters.

This matters a lot to the training of your NLP model. You could train a generative language model to predict the next sentence based on the preceding sentences, the next word based on the preceding words, or the next character based on the preceding characters.

Regardless, in both segmentation and tokenization, you’re decomposing a whole bunch of text down into individual units that your algorithm can work with.

Making the Case Consistent

It’s standard practice to make the case of your text consistent throughout, as this makes training simpler. This is usually done by lowercasing all the text, though we suppose if you’re feeling rebellious there’s no reason you couldn’t uppercase it (but the NLP engineers might not invite you to their fun Natural Language Parties if you do.)

Fixing Misspellings

NLP, like machine learning more generally, is only as good as its data. If you feed it text with a lot of errors in spelling, it will learn those errors and they’ll show up again later.

This probably isn’t something you’ll want to do manually, and if you’re using a popular language there’s likely a module you can use to do this for you. Python, for example, has TextBlob, Autocorrect, and Pyspellchecker libraries that can handle spelling errors.

Getting Rid of the Punctuation Marks

Natural language tends to have a lot of punctuation, with English utilizing dozens of marks such as ‘!’ and ‘;’ for emphasis and clarification. These are usually removed as part of preprocessing.

This task is something that can be handled with regular expressions (if you have the patience for it…), or you can do it with an NLP library like Natural Language Toolkit (NLTK).

Expanding the Contractions

Contractions are shortened versions of words, like turning “do not” into “don’t” or “would not” into “wouldn’t”. These, too, can be problematic for NLP algorithms and are usually removed during preprocessing.


In linguistics, the stem of a word is its root. The words “runs”, “ran”, and “running” all have the word “run” as their base.

Stemming is one of two approaches for reducing the myriad tenses of a word down into a single basic representation. The other is lemmatization, which we’ll discuss in the next section.

Stemming is the cruder of the two, and is usually done with an algorithm known as Porter’s Stemmer. This stemmer doesn’t always produce the stem you’d expect. “Cats” becomes “cat” while “ponies” becomes “poni”, for example. Nevertheless, this is probably sufficient for basic NLP tasks.


A more sophisticated version of stemming is lemmatization. A stemmer wouldn’t know the difference between the word “left” in “cookies are ahead and to the left” and “he left the book on the table”, whereas a lemmatizer would.

More generally, a lemmatizer uses language-specific context to handle very subtle distinctions between words, and this means it will usually take longer to run than a stemmer.

Whether it makes sense to use a stemmer or a lemmatizer will depend on the use case you’re interested in. Under most circumstances, lemmatizers are more accurate, and stemmers are faster.

Removing Extra White Spaces

It’ll often be the case that a corpus will have an inconsistent set of spacing conventions. This, too, is something algorithm will learn unless it’s remedied during preprocessing.
Removing Stopwords

This is a big one. “Stopwords” are words like “the” or “is” are all stopwords, and they’re almost always removed before training begins because they don’t add much in the way of useful information.

Because this is done so commonly, you can assume that the NLP library you’re using will have some easy way of doing it. NLTK, for example, has a native list of stopwords that can simply be imported:

from nltk.corpus import stopwords

With this, you can simply exclude the stopwords from the corpus.

Ditching the Digits

If you’re building an NLP application that processes data containing numbers, you’ll probably want to remove that as the training algorithm might end up inserting random digits here and there.

This, alas, is something that will probably need to be done with regular expressions.

Part of Speech Tagging

Part of speech tagging refers to the process of automatically tagging a word with extra grammatical information about whether it’s a noun, verb, etc.

This is certainly not something that you always have to do (we’ve completed a number of NLP projects where it never came up), but it’s still worth understanding what it is.

Supercharging Your NLP Applications

Natural language processing is an enormously powerful constellation of techniques that allow computers to do worthwhile work on text data. It can be used to build question-answering systems, tutors, chatbots, and much more.

But to get the most out of it, you’ll need to preprocess the data. No matter how much computing you have access to, machine learning isn’t of much use with bad data. Techniques like removing stopwords, expanding contractions, and lemmatization create corpora of text that can then be fed to NLP algorithms.

Of course, there’s always an easier way. If you’d rather skip straight to the part where cutting-edge conversational AI directly adds value to your business, you can also reach out to see what the Quiq platform can do.