Technology Partners

Our Team

Our Awards

Social Impact

Newsroom

Locations

Careers

About Us

Contact

Do Not Sell my Personal Information

Cookie Preferences

Culture Value Chain

iLabs Center for Innovation

Industries

Insights

Investor Relations

TELUS International is a subsidiary of: 

Privacy Shield Framework

Privacy Policy

Solutions

Subscribe to Newsletter

Website User Terms

logo-x

Icon facebook

Icon youtube

Icon linkedin

Technology

Financial Services & Fintech

Automotive

Healthcare

Communications & Media

Games

Retail & Ecommerce

Travel & Hospitality

infobrief

Guide

Resource Type Article

Article

case-studies thumb

Case Study

Preventing fraud for a global tech company in the travel and hospitality space image with fern in background

TI resource case 900x510

Video

whitepapers thumb

Research & Reports

checklists thumb

Checklist

brochures thumb

Brochure

ebooks thumb

E-book

Podcast Type Image

Podcast

The recent proliferation of generative AI (GenAI) models has sparked a lot of interest and excitement. These advanced large language models (LLMs) can do many extraordinary things — from crafting email responses to recommending a fitness routine to generating computer code; the list is seemingly endless.

However, these models aren't infallible. In fact, their propensity to sometimes hallucinate — a phenomenon where they provide responses that incorporate fabricated data that appears authentic — could significantly impact user trust. A recent TELUS International survey found that 61% of respondents were concerned about generative AI increasing the spread of inaccurate information online. 

Understanding what hallucinations are, why they happen and how to prevent them is critical to maintain users' trust in GenAI applications.

Introduction to generative AI hallucinations

A hallucination describes a model output that is either nonsensical or outright false. An example is asking a generative AI application for five examples of bicycle models that will fit in the back of your specific make of sport utility vehicle. If only three models exist, the GenAI application may still provide five — two of which are entirely fabricated. While this is a relatively low-stakes example of a hallucination, some could have far greater consequences. 

Recently a New York attorney representing a client's injury claim relied on a conversational chatbot to conduct his legal research. The federal judge overseeing the suit noted that six of the precedents quoted in his brief were bogus. It turns out that not only did the chatbot make them up, it even stipulated they were available in major legal databases.

While guardrails to prevent GenAI hallucinations need to be put in place, the first step is understanding how, or rather why, these inaccuracies happen.

Why do generative AI hallucinations occur?

While leading AI experts aren't entirely sure what causes hallucinations, there are several factors that are often cited as triggers.

First, hallucinations can occur if the training data used to develop the model is insufficient or includes large gaps leading to edge cases that are unfamiliar to the model. For example, in drafting a contract, a generative model that was fine-tuned using contracts from the financial services industry may not have sufficient exposure to terms and concepts in healthcare law to draft contracts for that industry. Most of the time, generative AI's primary goal is to produce an output in response to a prompt. Even if it doesn't "understand" the prompt, it might craft a response based on insufficient training data, thereby leading to a faulty result.

Similarly, some machine learning (ML) models suffer from overfitting, where the output is accurate for its training data, but inaccurate for new data. The goal of ML model training is to generalize from training instances so that the model can correctly operate on instances it hasn't seen before. Overfitting occurs when a model is trained to the point where it effectively memorizes the inputs and appropriate outputs for the training set, leaving it unable to generalize effectively to new data. For example, a model used to approve loan applications may be considered to be 90% accurate in predicting the likelihood of loan default. However, if it has been subject to overfitting, it likely has an accuracy rate closer to 70%. Therefore, applying the model to future loan decisions will result in a decrease in business profits and an increase in dissatisfied customers.

Another model development challenge is ensuring training texts and prompts are properly encoded. LLMs map terms to a set of numbers — a process known as a vector encoding — and these encodings have some key advantages over working with words directly. For example, words with multiple meanings can have one encoding per meaning, reducing the chance of ambiguity. So, the word "bank" would use one vector representation when referring to a financial institution and another when referring to the shore of a river. Vector representations also allow mapping semantic operations — like finding a similar word — into mathematical operations. Problems with encoding and decoding between text and representations can lead to hallucinations.

Best practices to prevent generative AI hallucinations

While generative AI hallucinations are a concerning issue, there are ways to reduce their frequency and intensity. Consider the following best practices.

The most obvious protection from hallucinations is high-quality input data. It's critical that your GenAI model is trained on a diverse and representative dataset that covers a wide range of real-world examples. Using sufficient, unbiased data is key to training an accurate, resilient model.

Another crucial part of the training process is incorporating human feedback, also known as reinforcement learning from human feedback (RLHF). Because AI models lack a nuanced understanding of language, they can produce responses that are out of context or irrelevant. RLHF provides models with regular corrections via feedback from people, so that an understanding of the world that only a human can have is incorporated into the training process.

Transparency in AI ensures that it's possible to understand a model's inner workings and how it makes decisions. The issue is coming to the forefront as LLMs evolve, particularly because more advanced models are harder to understand.

Users and machine learning professionals should be able to evaluate how a model was trained and review for potential weaknesses in the learning process. Transparency also makes it easier to identify and correct errors that can lead to hallucinations.

A malicious user of a generative AI system could experiment and probe a model looking for ways to make it hallucinate. It's necessary to incorporate counter measures to help monitor and control the types of inputs allowed in generative AI systems. These include using adversarial examples in the model's training to improve its ability to respond appropriately and to audit the model's anomaly detection capabilities. A further means is by data sanitization, which involves checking that no malicious inputs are being fed into the model. And finally, security updates and patches can help block external threats to your AI model.

While generative AI hallucinations are a frustrating hurdle that can significantly impact user trust, they aren't insurmountable. By training models using high-quality data, ensuring model transparency and enacting effective quality control, developers can improve their model's resiliency to deliver accurate predictions.

Hallucinations are an obstacle to building user trust in generative AI applications. Learn about the phenomenon, including best practices for prevention.

Single line drawing of the side profile of a head and the term "AI" imposed on a wavy background connoting hallucination

ai hallucination

Check out our solutions

Generative AI

Generative AI hallucinations: Why they occur and how to prevent them

6-steps-for-Conversational-Bot-success-A-primer 

Make the most of your conversational bot investment with our easy-to-follow guide featuring best practices that can be applied to your digital transformation journey.

A conversational bot floating above a mobile phone

(Hero) 6-steps-for-Conversational-Bot-success-A-primer hero

An illustration of a bot floating above a mobile phone

(Featured) 6-steps-for-Conversational-Bot-success-A-primer

Six steps for conversational bot success: A helpful primer for chatbot implementation

IDC Info Snapshot - Content Moderation thumbnail

In this IDC Info Snapshot, discover the benefits of engaging an experienced CX partner for content moderation to safeguard your online communities.

IDC Info Snapshot - content moderation hero

IDC Info Snapshot - content moderation feature image

Expanding content moderation capabilities helps fast-growing brands earn customer trust 

More and more brands are using machine learning and computer vision in their advertising. Discover the risks and benefits.

Illustration of people positioned around a larger-than-life target and laptop computer, symbolizing digital advertising.

Ad data

How to improve online ads with AI data

A copy of the Digital customer experience priorities in 2023 report on top of a green leafy plant.

Digital Customer Experience Priorities 2023 Preview Image

TELUS International, in partnership with Statista, surveyed 250 enterprise leaders to explore where they plan to invest in digital customer experience (CX) technology in 2023. Uncover the results.

An illustrated representation of customer profiles and leaving a five-star review online.

Digital Customer Experience Priorities 2023 Hero

Survey results: Digital customer experience priorities for leaders in 2023

Improving search relevance for a fast-growing unicorn

Want to speak with an expert?

Learn how TELUS International classified over 200,000 search queries for a leading online travel company which provides a one-stop platform for a range of ticketing services including flights, accommodation and attractions.

Data Validation & Relevance

A recommender system uses machine learning to predict the likelihood that a user will prefer a particular item or service. Learn how these systems facilitate great experiences that keep customers coming back for more.

Cartoon of a banner that reads "Recommended" and a person hand and arm giving a "thumbs up" gesture

Recommender systems

How do recommender systems facilitate great CX?

Facilitating transactional review and online shopping services for a global tech giant

Examine how TELUS International evaluated high-quality data and merchant ratings to enhance the customer experience.

Feature image of person shopping online with phone and laptop 

Deploying automation to assist agents at a consumer robotics company image with fern in background

Preview image: Deploying automation to assist agents at a consumer robotics company

Help your agents reach their full potential with automation

Even consumer robotics companies can benefit from a little help deploying customer experience (CX) automation. Learn more about TELUS International’s solution to improve a client’s agent efficiency and engagement.

Learn about how we helped a consumer robotics company improve their digital customer experience with agent-facing automation.

PDF for case study titled "Deploying automation to assist agents at a consumer robotics company"

Deploying automation to assist agents at a consumer robotics company

Illustration of consumer robotics including a butler, a chef and cat riding a robot vacuum.

AI Bots

In this virtual chat with TELUS International computer vision experts Ajinkya Malasane and Kaushik PS, we’ll dive deep into end-to-end sensor fusion data collection and annotation solutions for autonomous vehicle training needs.

Three cars on road with labeling boxes around them

3d data annotation

Leveraging automation for labeling large 3D pipelines

The cover of The future of content moderation: Strategies and tools for 2023 and beyond e-book with a fern in the background.

The future of content moderation: Strategies and tools for 2023 and beyond

Organizations have a responsibility to create and maintain digital experiences that are truthful, welcoming and safe. Learn how brands can keep pace with the growing levels of user-generated content (UGC) to build trust with their customers and protect their reputation.

An illustration of various people creating user generated content on their phones.

Preview image of the Forrester report "How To Set CX Metrics Goals" and a plant

TI Resource ForresterReport

Gain an understanding of the challenges faced by customer experience (CX) leaders in setting goals for their metrics — and effective techniques to persevere.

Illustration of a person and various graphs and scales symbolizing metrics, measurement and KPIs

Hero image for Forrester - How to set CX metrics goals - 1620x550

Forrester - How to set CX metrics goals - card image

How to set CX metrics goals

Online research is a cornerstone of the modern travel experience. From TikTok reels to Google Reviews, you would be hard-pressed to find a customer who hasn't combed the internet for inspiration before booking a flight or making a hotel reservation.

According to Expedia's report, The Path To Purchase, travelers view 141 pages of travel content in the 45 days prior to booking a trip on average. The same report also revealed that "page views span content across various website categories, with online travel agencies accounting for nearly half of these page views (67 pages), followed by airline websites (33 pages), hotel websites (16 pages) and meta travel websites (16 pages)."

With travelers spending an extensive amount of time both creating and consuming online content, it is more important than ever for travel and hospitality brands to ensure their customers are receiving accurate information. A robust content moderation strategy is key to establishing trust with guests well before arrival — and maintaining it long past departure.

The growth of user-generated travel content

If you traveled to Rome and didn't post an Instagram picture of a coin being tossed into the Trevi Fountain, did it even really happen? Travelers today are producing online user-generated content (UGC) at exuberant rates, and with this behavior has come the steady decline of published travel guides in favor of travel hashtags.

This new avenue to connect directly with consumers is an exciting business opportunity, providing brands with authentic fresh content that can be used in marketing, personalized customer service and enhanced user interfaces. In fact, travel marketing company Phocuswright conducted a survey of more than 1,000 travelers and found that 72% of travelers are more likely to book a hotel after seeing UGC, while 63% of travelers say they've booked a hotel based on a photo they saw on social media.

On the flip side, however, a survey by TELUS International found that more than 40% of respondents said they would disengage from a brand's community after as little as one exposure to fake UGC, while 45% said they would lose all trust in a brand.

The stakes are high when it comes to user-generated content. Fortunately, with the right content moderation processes in place, you'll be able to protect your brand and enhance the overall customer experience

Four ways content moderation can improve the user experience for travel and hospitality guests

In crafting a comprehensive content moderation strategy, certain focal points emerge as crucial considerations. The following are four critical opportunities for travel brands to integrate content moderation into their operations.

Travelers rely heavily on reviews to make informed decisions about their trips and accommodations. According to a survey by TripAdvisor, "Traveler reviews remain a go-to source of information, with 72% of respondents always or frequently reading reviews before making a decision on places to stay and eat, or things to do. The figure is even higher when it comes to accommodation bookings, with four out of five participating travelers (81%) always or frequently reading reviews before booking a place to stay."

Verified and legitimate reviews help maintain a positive image, while fraudulent or biased reviews can tarnish a brand's reputation. For travelers, it can often be hard to tell the difference between a legitimate review and a fake one. Having a robust content moderation strategy in place to identify and combat fake reviews ensures travelers receive accurate information, enables them to plan their trips with confidence and preserves the integrity of the review system.

While the digital transformation of the travel and hospitality industry created new and convenient ways for brands to do business with consumers, it also created new opportunities for bad actors to exploit these channels for their gain. According to Autohost, an online booking verification provider, globally, the hospitality industry generates an estimated $3 trillion of revenue per year. And according to the Association of Certified Fraud Examiners, between 5-6% of this annual revenue is lost to fraud. That amounts to $150 billion in direct loss of revenue.

But monetary losses aren't the only risks associated with fraudulent activity in the travel and hospitality sector. A travel brand's reputation hinges on the trust and credibility it establishes with travelers and guests. If fraudulent activities are allowed to proliferate unchecked, it erodes trust and damages the brand's reputation as customers become wary of engaging with a potentially untrustworthy entity. Fake listings for accommodations, tours and travel packages, phishing scams and too-good-to-be-true discounts are all examples of fraudulent activities that could tarnish a brand's reputation. Having the right technology, along with a team of expert moderators, can help assess content for inconsistencies, duplicate information or suspicious details, reducing the chance that travelers will fall victim to fraudulent offers.

Validating that a profile of a user set up online is authentic is vital to creating vibrant digital communities. Fraudsters may create fake online profiles to write misleading reviews, share inappropriate content or in an attempt to scam other users.

It is up to brands to take profile moderation seriously. Verification processes using artificial intelligence-enabled technology can be implemented to ensure the identity of users posting listings or advertisements. For example, checks can be completed to verify that user information matches official records by requesting that new users submit copies of government identification and an additional photo when creating a profile to reduce the risk of impersonation.

Online travel forums and marketplaces have become a popular location for travelers to share their reviews, recommendations, travel stories and more. While these communities provide great outlets for travelers to come together to engage with fellow members who have similar travel preferences and experiences, it is essential that the UGC posted in these forums adheres to the community guidelines set. Inappropriate images or language can quickly turn a constructive and helpful conversation into a toxic environment, negatively impacting user experiences.

Strategies for content moderation in travel and hospitality

Between review sites, social media communities, online forums, blog posts and videos, there's a significant amount of UGC to sort through. Fortunately, brands are able to turn to technology, like artificial intelligence (AI), to support at scale.

Technology can be leveraged for content moderation in various ways, including, but not limited to:

Automated filtering: Algorithms are used to detect and flag potentially spammy or inappropriate content in real-time, helping brands quickly identify and address problematic content before it becomes visible to users.

Real-time alerts: To enable brands to take immediate action against concerning UGC, real-time alerts can be set up to notify moderators.

Keyword detection: Specific keywords or phrases that might be indicative of inappropriate content are identified and used to flag potential issues for human review.

Sentiment analysis: Tools can be leveraged to assess the emotional tone of UGC. This helps identify positive and negative sentiments, enabling brands to respond appropriately to customer feedback.

User-behavior analysis: User behavior patterns can be analyzed to identify suspicious or fraudulent activity. Unusual posting frequency, duplicate content or rapid changes in profile details can be indicators of potentially harmful behavior.

Content queues: Technology can be utilized to organize and prioritize content for human moderation, streamlining the workflow for moderators and ensuring that potentially problematic content is addressed promptly.

While technology plays an important role in content moderation, it's not enough by itself. A robust content moderation strategy should implement a human-in-the-loop approach where technology is combined with human judgment.

Brands operating in the travel and hospitality marketplace face unique challenges compared to brands that may not be catering to such a global audience. Not only do travel brands need to have a geographic strategy for their content moderation operations, but they need to have the ability to moderate UGC in multiple languages and have the capabilities to keep social and cultural nuances in mind when doing so. For example, a phrase shared online might be innocuous in one country, but mean something entirely different in another. Human moderators have an unparalleled ability to identify content violations in the context of culture, current events and brand regulations and they outperform AI in identifying the emotion and intent behind digital content.

Crafting an effective content moderation strategy that tackles the aforementioned challenges can indeed be a complex endeavor for brands. However, leveraging the expertise of a qualified trust and safety partner that understands the intricacies of content moderation, has a global presence and a team of tenured, multilingual content moderators can empower brands to start their content moderation journey off on the right foot. Contact our experts to discuss how we can help your brand's content moderation operations take off.

Uncover how travel and hospitality brands can combat fake reviews, scams and more with a robust content moderation strategy.

Airplane leaving a trail of five stars, meant to symbolize positive customer experiences in the travel and hospitality industry

travel como3

Content Moderation Solutions

Four ways content moderation can build trust for travel and hospitality brands

Preview image of the case study "Creating annotation work opportunities through impact sourcing" with plant in background. 

resource annotation impact sourcing

Discover how TELUS International and the SETU Foundation spearheaded an initiative to provide occupational and learning opportunities to young women in India while delivering high-quality results for the client.

Two women sit in front of computer monitors doing annotation work.

annotation impact sourcing

Creating annotation work opportunities through impact sourcing

On this episode, we discuss the connection between cybersecurity and digital customer experience — and how rethinking data security can help maintain customer trust.

Episode cover image for Questions for now, a TELUS International podcast, featuring an illustrated character holding a phone and giving a verified business profile a five-star review.

Questions for now data security image

How can brands rethink data security to maintain customer trust?

Preview image of the report "CX outsourcing in 2023" accompanied by a plant

TI Resource WhitePaper 2023

Delve into new insights about customer experience outsourcing from a survey of 712 enterprise executives with strategic decision-making authority.

Illustration of customer support agents surrounded by related iconography like charts, star ratings and text boxes.

CX Outsourcing2023 Hero Image

Cover image for the dynamic report "CX outsourcing in 2023" featuring the title and illustrations of customer support agents and related iconography 

CX Outsourcing in 2023

Executive survey results: CX outsourcing in 2023

TI resource eBook 800x450 The essential guide to training data 

Discover best practices for the sourcing, labeling and analyzing of training data from TELUS International, a leading provider of AI data solutions.

guide to AI training data - website hero image 

The essential guide to AI training data

Join experts from TELUS International and Automation Anywhere, a top cloud automation platform, to learn how banks and financial services firms can leverage automation to enhance the customer experience, optimize operations and foster customer loyalty.

An illustration showing various digital automation technologies for banking including, artificial intelligence, mobile payments, chatbots and data analytics.

The future of banking and financial services webinar

The future of banking and financial services: Unlocking customer experience potential with intelligent automation

Preview image for case study "Aligning content moderation operations to new legislation for a games client" with a plant in the background

Case Study Content Moderation Legislation

Learn about TELUS International's work helping a successful games company maintain player safety on its social media channels with content moderation.

Image of several people huddled around a gaming computer with floating icons like a controller

Improving search relevance for a fast-growing unicorn

Share