Connect with us

SEO

Everything You Need To Know

Published

on

Everything You Need to Know

Maybe you’ve heard colleagues or industry experts talking about Microsoft Clarity. But what is it and how does it work?

Microsoft Clarity is a user behavior and website debugging analytics tool unlike any other.

What Clarity does is provide insights into how users interact with the site, making it completely different from other analytics tools, including Google Analytics.

Learn about its various features, limitations, why it’s not a competitor to Google Analytics, and how you can make the best use of Microsoft Clarity here.

User Experience Analytics

Other analytics tools focus on things like reporting on traffic, keywords, page popularity, and so on.

Microsoft Clarity focuses on the user experience to help publishers gain insights into how users are interacting with their site.

The user behavior data helps publishers identify areas to improve, find web page bugs, and gain insights into conversions, among many other useful insights.

Microsoft Clarity even provides machine learning and deep AI components in the background that automatically generate insights based on patterns created by website user behaviors. It provides these insights as suggestions for further investigation and tracking.

With Clarity, a publisher can see user engagement patterns on different parts of individual pages and can play back user sessions to learn how users interact with web pages.

Over 25 filters make it easy to zero in on user pain points to debug website issues or discover what works in order to replicate that experience on other pages.

All of these insights are delivered by Microsoft Clarity in near real-time.

Microsoft Clarity Versus Google Analytics

You might wonder whether you need Microsoft Clarity if you already have Google Analytics. Some believe that because they’re both analytics services, there may be overlap between the two.

However, there really is no comparison between Google Analytics and Microsoft Clarity because they do very different things.

Google Analytics provides insights into traffic patterns.

Microsoft Clarity provides actionable insights into how users interact with web pages.

Microsoft Clarity is not a competitor of Google Analytics. Instead, it actually complements Google Analytics to the point that you can connect Google Analytics to Clarity and gain even more user behavior insights using the imported data.

Privacy Compliance

Although Microsoft Clarity tracks user behavior on the website, Clarity is fully compliant with the European GDPR and the California CCPA privacy requirements.

Microsoft Clarity Impact On Page Speed

Microsoft Clarity’s JavaScript is loaded asynchronously and, according to Microsoft, does not impact website performance.

Microsoft says:

“Visitors to your site won’t experience any difference in site speed or performance. The Clarity JavaScript is asynchronous so it does not slow down the page load time.”

Does Microsoft Clarity Have Traffic Limitations?

There are no limits to the amount of traffic that can be measured by Clarity.

Unlike other heatmap and analytics tools that impose traffic limits to the free versions of their tools, Microsoft imposes no limits based on traffic.

According to Microsoft:

“There are absolutely no limits on the number of sites per account. Clarity can scale to support even the largest websites.

Clarity process more than 1 petabyte of data from over 100 million users per month. Also, there are no traffic limits on these sites.”

Microsoft Clarity Features

The main features of Microsoft Clarity are:

  • Clarity Heatmaps.
  • Session Recordings.
  • Clarity Insights.

Clarity Heatmaps

Clarity Heatmaps provides two kinds of heatmap data:

1. Click Heatmaps

Click heatmaps:

  • Show engagement levels of different parts of a webpage.
  • Reveal where people are clicking (including non-clickable page elements).
  • And provide an idea of which page elements are important to most site visitors.

Click heatmap data can be shown for a single page or for a group of pages.

This data can be further refined and segmented with filters to drill down and see how different users are clicking on web page elements.

Screenshot of Microsoft Clarity Heatmaps, October 2020

2. Scroll Heatmaps

Scroll Heatmaps show how far users are scrolling on a web page. Like all the other Clarity features, filters can be applied to the Scroll Heatmap in order to see how different users scroll through a page – by device, for example.

Scroll Heatmap data is incredibly useful because it can show how far users are scrolling before they click a call to action.

The Scroll heatmaps can also help identify if users aren’t reaching a call to action or important information.

If users aren’t reaching certain content and are backing out of the site without converting, then the scroll heatmap data will show at which point users are bailing on your site.

Actionable Heatmap Data

The Clarity Heatmaps can be segmented by filters such as traffic sources, devices, and browsers to identify patterns displayed by different visitors.

The heatmap data is useful for debugging web page issues by identifying where they are clicking, better understanding the user experience, and identifying where users linger.

Additionally, it helps to improve conversions by showing where users are bailing or if call to actions are scrolled past and not stimulating clicks.

In my opinion, the most important quality of the Clarity Heatmaps feature is helping to improve conversions because most sites have a conversion action they want users to complete whether it’s clicking an ad, buying a product, clicking an affiliate link, or signing up for a newsletter.

The Clarity Heatmap helps debug conversion issues and improve them.

The information in Clarity Heatmaps can also be shared with others in your company and with clients.

There are no traffic limits to the Clarity Heatmap feature, which makes it an attractive feature for publishers with large amount of traffic and those starting out.

Session Recordings

Clarity session recordings is a feature that records and plays back user journeys through the web site. It shows how users interact with site navigation, calls to action, search features, and other on-page elements.

Session recordings shows publishers if site navigation and links help users find the content they want and can also show what on-page factors aren’t working, like the calls to action.

Screenshot of Session TimelineScreenshot of a User Session Timeline, October 2020

The session recordings can identify rage clicks, dead clicks, quick backs, and excessive scrolling.

Rage Clicks

Rage clicks indicate areas of a web page that may not be interactive when a user expects them to be. The typical rage click is characterized when a user repeatedly clicking on a web page element like a link, button, or image.

For example, if a link isn’t working because the page hasn’t fully loaded or an image seems like a link but it isn’t one at all. Rage clicks are highlighted by Clarity to point out areas of the user experience that indicate user frustration with the web page.

Dead Clicks

A dead click is what happens when an interactive element does not respond in a reasonable amount of time or doesn’t respond at all.

This is also a signal of user frustration.

Quick Backs

The quick back is when a user clicks away from your site to another site but then returns.

Microsoft indicates that this data point will be updated to include the origin site so that it will record when a user clicks from one page in a site to another page in the same site and then returns to the original page, indicating dissatisfaction with the page they clicked to.

Excessive Scrolling

Session recordings can also reveal what Microsoft calls “excessive scrolling.”

Excessive scrolling is when Clarity detects that a site visitor scrolls up and down in an unusual pattern that indicates a poor user experience.

This data point could indicate that the user is not finding what they expect to find and is likely frustrating the site visitor in some other way, enough to cause them to leave the site.

Clarity Session Recordings provide valuable insights that can help increase sales, affiliate clicks, ad clicks, and site visitor satisfaction.

A useful feature of Session Recordings is that these data points can be segmented by browser, campaign, and 23 other filters.

Clarity Session recordings is a powerful way to gain insights into user behavior and improve web page and website performance.

Clarity Analytics Recordings DashboardScreenshot of the Recordings Dashboard, October 2020

The session timeline, shown in the screenshot above, is like a movie of the user interaction with a page. Cursor movements are shown.

The session panel on the left allows a publisher to filter the data to isolate a wide range of data types.

The individual sessions seen in the boxes can be selected and viewed.

Additionally, one can click on the Filters button at the top in order to select for a large amount of data types, like user device and so on.

Clicking on the Filters button results in an entire web page of filters.

To save space and provide a closeup, I sliced the filters page in half, a left side and a right side.

Microsoft Clarity Analytics Sessions FilterScreenshot of the Left and Right Side of the Filters, October 2020

Clarity Insights

Microsoft Clarity Insights is a feature that applies the power of Deep AI and Machine Learning algorithms to automatically surface actionable insights from the analytics data collected by Clarity.

Screenshot of the Microsoft Clarity Screenshot of Insights Dashboard, October 2020

Clarity watches for session recordings with JavaScript errors, rage clicks, and dead clicks, as well as identifies browsers and also user groups to watch.

Users can save groups for tracking.

The Clarity Insights documentation says:

“Clarity Insights are a set of Machine Learning (ML) based filters and recommendations on what content should be most important for you.

…Through the dashboard, you can understand the users without having to analyze the ocean of data derived from user interactions on the website.

There comes a central question: If Clarity can record every user interaction, how can it surface the sessions and pages that matter the most? One solution comes via the Clarity Insights platform.

Clarity Insights lean on Microsoft’s decades of experience in Data Science and Machine Learning to identify key trends and patterns in your site activity.

…Providing accurate, accessible, and proactive analytics is a foundational feature of Clarity.”

Screenshot of a closeup of the Microsoft Clarity Screenshot of a closeup of the Microsoft Clarity “Insights” dashboard, October 2020

Adding Microsoft Clarity Analytics To Your Stack

The big question many have is whether they should use Clarity considering that they already use another analytics program.

Clarity provides actionable insights for improving website earnings and the user experience, which is something many analytics programs do not provide.

It’s clear that Microsoft Clarity is not a competitor to Google Analytics, it is complementary to it.

Thus, it could be said that it is not appropriate to compare the two because they both solve different problems.

Clarity is a good product because it helps publishers improve conversions and sales, as well as the site visitor user experience.

What Clarity does is to help publishers identify shortcomings in their site(s) and improve them.

There is no pricing model for Microsoft Clarity – it is free, regardless of how much traffic a site attracts.

The only limitation to Clarity is that financial, government, and medical websites are not recommended by Microsoft to onboard to Clarity.

The answer to the question of whether you should use Microsoft Clarity, aside from the above caveat, depends on how important it is to you to improve earnings and site visitor user experience.

Citations:

More resources:


Featured Image: Ollyy/Shutterstock




Source link

Keep an eye on what we are doing
Be the first to get latest updates and exclusive content straight to your email inbox.
We promise not to spam you. You can unsubscribe at any time.
Invalid email address
Click to comment

You must be logged in to post a comment Login

Leave a Reply

SEO

Mozilla VPN Security Risks Discovered

Published

on

By

Mozilla VPN Security Risks Discovered

Mozilla published the results of a recent third-party security audit of its VPN services as part of it’s commitment to user privacy and security. The survey revealed security issues which were presented to Mozilla to be addressed with fixes to ensure user privacy and security.

Many search marketers use VPNs during the course of their business especially when using a Wi-Fi connection in order to protect sensitive data, so the  trustworthiness of a VNP is essential.

Mozilla VPN

A Virtual Private Network (VPN), is a service that hides (encrypts) a user’s Internet traffic so that no third party (like an ISP) can snoop and see what sites a user is visiting.

VPNs also add a layer of security from malicious activities such as session hijacking which can give an attacker full access to the websites a user is visiting.

There is a high expectation from users that the VPN will protect their privacy when they are browsing on the Internet.

Mozilla thus employs the services of a third party to conduct a security audit to make sure their VPN is thoroughly locked down.

Security Risks Discovered

The audit revealed vulnerabilities of medium or higher severity, ranging from Denial of Service (DoS). risks to keychain access leaks (related to encryption) and the lack of access controls.

Cure53, the third party security firm, discovered and addressed several risks. Among the issues were potential VPN leaks to the vulnerability of a rogue extension that disabled the VPN.

The scope of the audit encompassed the following products:

  • Mozilla VPN Qt6 App for macOS
  • Mozilla VPN Qt6 App for Linux
  • Mozilla VPN Qt6 App for Windows
  • Mozilla VPN Qt6 App for iOS
  • Mozilla VPN Qt6 App for Androi

These are the risks identified by the security audit:

  • FVP-03-003: DoS via serialized intent
  • FVP-03-008: Keychain access level leaks WG private key to iCloud
  • VP-03-010: VPN leak via captive portal detection
  • FVP-03-011: Lack of local TCP server access controls
  • FVP-03-012: Rogue extension can disable VPN using mozillavpnnp (High)

The rogue extension issue was rated as high severity. Each risk was subsequently addressed by Mozilla.

Mozilla presented the results of the security audit as part of their commitment to transparency and to maintain the trust and security of their users. Conducting a third party security audit is a best practice for a VPN provider that helps assure that the VPN is trustworthy and reliable.

Read Mozilla’s announcement:
Mozilla VPN Security Audit 2023

Featured Image by Shutterstock/Meilun

Source link

Keep an eye on what we are doing
Be the first to get latest updates and exclusive content straight to your email inbox.
We promise not to spam you. You can unsubscribe at any time.
Invalid email address
Continue Reading

SEO

Link Building Outreach for Noobs

Published

on

Link Building Outreach for Noobs

Link outreach is the process of contacting other websites to ask for a backlink to your website.

For example, here’s an outreach email we sent as part of a broken link building campaign:

In this guide, you’ll learn how to get started with link outreach and how to get better results. 

How to do link outreach

Link outreach is a four-step process:

1. Find prospects

No matter how amazing your email is, you won’t get responses if it’s not relevant to the person you’re contacting. This makes finding the right person to contact equally as important as crafting a great email.

Who to reach out to depends on your link building strategy. Here’s a table summarizing who you should find for the following link building tactics:

As a quick example, here’s how you would find sites likely to accept your guest posts:

  1. Go to Content Explorer
  2. Enter a related topic and change the dropdown to “In title”
  3. Filter for English results
  4. Filter for results with 500+ words
  5. Go to the “Websites” tab
Finding guest blogging opportunities via Content ExplorerFinding guest blogging opportunities via Content Explorer

This shows you the websites getting the most search traffic to content about your target topic.

From here, you’d want to look at the Authors column to prioritize sites with multiple authors, as this suggests that they may accept guest posts.

The Authors column indicate how many authors have written for the siteThe Authors column indicate how many authors have written for the site

If you want to learn how to find prospects for different link building tactics, I recommend reading the resource below.

2. Find their contact details

Once you’ve curated a list of people to reach out to, you’ll need to find their contact information.

Typically, this is their email address. The easiest way to find this is to use an email lookup tool like Hunter.io. All you need to do is enter the first name, last name, and domain of your target prospect. Hunter will find their email for you:

Finding Tim's email with Hunter.ioFinding Tim's email with Hunter.io

To prevent tearing your hair from searching for hundreds of emails one-by-one, most email lookup tools allow you to upload a CSV list of names and domains. Hunter also has a Google Sheets add-on to make this even easier.

Using the Hunter for Sheets add-on to find emails in bulk directly in Google SheetsUsing the Hunter for Sheets add-on to find emails in bulk directly in Google Sheets

3. Send a personalized pitch

Knowing who to reach out to is half the battle won. The next ‘battle’ to win is actually getting the person to care.

Think about it. For someone to link to you, the following things need to happen:

  • They must read your email
  • They must be convinced to check out your content
  • They must open the target page and complete all administrative tasks (log in to their CMS, find the link, etc.)
  • They must link to you or swap out links

That’s a lot of steps. Most people don’t care enough to do this. That’s why there’s more to link outreach than just writing the perfect email (I’ll cover this in the next section).

For now, let’s look at how to craft an amazing email. To do that, you need to answer three questions:

  1. Why should they open your email? — The subject line needs to capture attention in a busy inbox.
  2. Why should they read your email? — The body needs to be short and hook the reader in.
  3. Why should they link to you? — Your pitch needs to be compelling: What’s in it for them and why is your content link-worthy?

For example, here’s how we wrote our outreach email based on the three questions:

An analysis of our outreach email based on three questionsAn analysis of our outreach email based on three questions

Here’s another outreach email we wrote, this time for a campaign building links to our content marketing statistics post:

An analysis of our outreach email based on three questionsAn analysis of our outreach email based on three questions

4. Follow up, once

People are busy and their inboxes are crowded. They might have missed your email or read it and forgot.

Solve this by sending a short polite follow-up.

Example follow-up emailExample follow-up email

One is good enough. There’s no need to spam the other person with countless follow-up emails hoping for a different outcome. If they’re not interested, they’re not interested.

Link outreach tips

In theory, link outreach is simply finding the right person and asking them for a link. But there is more to it than that. I’ll explore some additional tips to help improve your outreach.

Don’t over-personalize

Some SEOs swear by the sniper approach to link outreach. That is: Each email is 100% customized to the person you are targeting.

But our experience taught us that over-personalization isn’t better. We ran link-building campaigns that sent hyper-personalized emails and got no results.

It makes logical sense: Most people just don’t do favors for strangers. I’m not saying it doesn’t happen—it does—but rarely will your amazing, hyper-personalized pitch change someone’s mind.

So, don’t spend all your time tweaking your email just to eke out minute gains.

Avoid common templates

My first reaction seeing this email is to delete it:

A bad outreach emailA bad outreach email

Why? Because it’s a template I’ve seen many times in my inbox. And so have many others.

Another reason: Not only did he reference a post I wrote six years ago, it was a guest post, i.e., I do not have control over the site. This shows why finding the right prospects is important. He even got my name wrong.

Templates do work, but bad ones don’t. You can’t expect to copy-paste one from a blog post and hope to achieve success.

A better approach is to use the scoped shotgun approach: use a template but with dynamic variables.

Email outreach template with dynamic variablesEmail outreach template with dynamic variables

You can do this with tools like Pitchbox and Buzzstream.

This can help achieve a decent level of personalization so your email isn’t spammy. But it doesn’t spend all your time writing customized emails for every prospect.

Send lots of emails

When we polled 800+ people on X and LinkedIn about their link outreach results, the average conversion rate was only 1-5%.

Link outreach conversion rates in 2023Link outreach conversion rates in 2023

This is why you need to send more emails. If you run the numbers, it just makes sense:

  • 100 outreach emails with a 1% success rate = 1 link
  • 1,000 outreach emails with a 1% success rate = 10 links

I’m not saying to spam everyone. But if you want more high-quality links, you need to reach out to more high-quality prospects.

Build a brand

A few years ago, we published a link building case study:

  • 515 outreach emails
  • 17.55% reply rate
  • 5.75% conversion rate

Pretty good results! Except the top comments were about how we only succeeded because of our brand:

Comments on our YouTube video saying we succeeded because of our brandComments on our YouTube video saying we succeeded because of our brand

It’s true; we acknowledge it. But I think the takeaway here isn’t that we should repeat the experiment with an unknown website. The takeaway is that more SEOs should be focused on building a brand.

We’re all humans—we rely on heuristics to make judgments. In this case, it’s branding. If your brand is recognizable, it solves the “stranger” problem—people know you, like you, and are more likely to link.

The question then: How do you build a brand?

I’d like to quote our Chief Marketing Officer Tim Soulo here:

What is a strong brand if not a consistent output of high-quality work that people enjoy? Ahrefs’ content team has been publishing top-notch content for quite a few years on our blog and YouTube channel. Slowly but surely, we were able to reach tens of millions of people and instill the idea that “Ahrefs’ content = quality content”—which now clearly works to our advantage.

Tim SouloTim Soulo

Ahrefs was once unknown, too. So, don’t be disheartened if no one is willing to link to you today. Rome wasn’t built in a day.

Trust the process and create incredible content. Show it to people. You’ll build your brand and reputation that way.

Build relationships with people in your industry

Outreach starts before you even ask for a link.

Think about it: People don’t do favors for strangers but they will for friends. If you want to build and maintain relationships in the industry, way before you start any link outreach campaigns.

Don’t just rely on emails either. Direct messages (DMs) on LinkedIn and X, phone calls—they all work. For example, Patrick Stox, our Product Advisor, used to have a list of contacts he regularly reached out to. He’d hop on calls and even send fruit baskets.

Create systems and automations

In its most fundamental form, link outreach is really about finding more people and sending more emails.

Doing this well is all about building systems and automations.

We have a few videos on how to build a team and a link-building system, so I recommend that you check them out.

Final thoughts

Good link outreach is indistinguishable from good business development.

In business development, your chances of success will increase if you:

  • Pitch the right partners
  • Have a strong brand
  • Have prior relationships with them
  • Pitch the right collaboration ideas

The same goes for link outreach. Follow the principles above and you will see more success for your link outreach campaigns.

Any questions or comments? Let me know on Twitter X.



Source link

Keep an eye on what we are doing
Be the first to get latest updates and exclusive content straight to your email inbox.
We promise not to spam you. You can unsubscribe at any time.
Invalid email address
Continue Reading

SEO

Research Shows Tree Of Thought Prompting Better Than Chain Of Thought

Published

on

By

Research Shows Tree Of Thought Prompting Better Than Chain Of Thought

Researchers discovered a way to defeat the safety guardrails in GPT4 and GPT4-Turbo, unlocking the ability to generate harmful and toxic content, essentially beating a large language model with another large language model.

The researchers discovered that the use of tree-of-thought (ToT)reasoning to repeat and refine a line of attack was useful for jailbreaking another large language model.

What they found is that the ToT approach was successful against GPT4, GPT4-Turbo, and PaLM-2, using a remarkably low number of queries to obtain a jailbreak, on average less than thirty queries.

Tree Of Thoughts Reasoning

A Google research paper from around May 2022 discovered Chain of Thought Prompting.

Chain of Thought (CoT) is a prompting strategy used on a generative AI to make it follow a sequence of steps in order to solve a problem and complete a task. The CoT method is often accompanied with examples to show the LLM how the steps work in a reasoning task.

So, rather than just ask a generative AI like Midjourney or ChatGPT to do a task, the chain of thought method instructs the AI how to follow a path of reasoning that’s composed of a series of steps.

Tree of Thoughts (ToT) reasoning, sometimes referred to as Tree of Thought (singular) is essentially a variation and improvement of CoT, but they’re two different things.

Tree of Thoughts reasoning is similar to CoT. The difference is that rather than training a generative AI to follow a single path of reasoning, ToT is built on a process that allows for multiple paths so that the AI can stop and self-assess then come up with alternate steps.

Tree of Thoughts reasoning was developed in May 2023 in a research paper titled Tree of Thoughts: Deliberate Problem Solving with Large Language Models (PDF)

The research paper describes Tree of Thought:

“…we introduce a new framework for language model inference, Tree of Thoughts (ToT), which generalizes over the popular Chain of Thought approach to prompting language models, and enables exploration over coherent units of text (thoughts) that serve as intermediate steps toward problem solving.

ToT allows LMs to perform deliberate decision making by considering multiple different reasoning paths and self-evaluating choices to decide the next course of action, as well as looking ahead or backtracking when necessary to make global choices.

Our experiments show that ToT significantly enhances language models’ problem-solving abilities…”

Tree Of Attacks With Pruning (TAP)

This new method of jailbreaking large language models is called Tree of Attacks with Pruning, TAP. TAP uses two LLMs, one for attacking and the other for evaluating.

TAP is able to outperform other jailbreaking methods by significant margins, only requiring black-box access to the LLM.

A black box, in computing, is where one can see what goes into an algorithm and what comes out. But what happens in the middle is unknown, thus it’s said to be in a black box.

Tree of thoughts (TAP) reasoning is used against a targeted LLM like GPT-4 to repetitively try different prompting, assess the results, then if necessary change course if that attempt is not promising.

This is called a process of iteration and pruning. Each prompting attempt is analyzed for the probability of success. If the path of attack is judged to be a dead end, the LLM will “prune” that path of attack and begin another and better series of prompting attacks.

This is why it’s called a “tree” in that rather than using a linear process of reasoning which is the hallmark of chain of thought (CoT) prompting, tree of thought prompting is non-linear because the reasoning process branches off to other areas of reasoning, much like a human might do.

The attacker issues a series of prompts, the evaluator evaluates the responses to those prompts and then makes a decision as to what the next path of attack will be by making a call as to whether the current path of attack is irrelevant or not, plus it also evaluates the results to determine the likely success of prompts that have not yet been tried.

What’s remarkable about this approach is that this process reduces the number of prompts needed to jailbreak GPT-4. Additionally, a greater number of jailbreaking prompts are discovered with TAP than with any other jailbreaking method.

The researchers observe:

“In this work, we present Tree of Attacks with Pruning (TAP), an automated method for generating jailbreaks that only requires black-box access to the target LLM.

TAP utilizes an LLM to iteratively refine candidate (attack) prompts using tree-of-thoughts reasoning until one of the generated prompts jailbreaks the target.

Crucially, before sending prompts to the target, TAP assesses them and prunes the ones unlikely to result in jailbreaks.

Using tree-of-thought reasoning allows TAP to navigate a large search space of prompts and pruning reduces the total number of queries sent to the target.

In empirical evaluations, we observe that TAP generates prompts that jailbreak state-of-the-art LLMs (including GPT4 and GPT4-Turbo) for more than 80% of the prompts using only a small number of queries. This significantly improves upon the previous state-of-the-art black-box method for generating jailbreaks.”

Tree Of Thought (ToT) Outperforms Chain Of Thought (CoT) Reasoning

Another interesting conclusion reached in the research paper is that, for this particular task, ToT reasoning outperforms CoT reasoning, even when adding pruning to the CoT method, where off topic prompting is pruned and discarded.

ToT Underperforms With GPT 3.5 Turbo

The researchers discovered that ChatGPT 3.5 Turbo didn’t perform well with CoT, revealing the limitations of GPT 3.5 Turbo. Actually, GPT 3.5 performed exceedingly poorly, dropping from 84% success rate to only a 4.2% success rate.

This is their observation about why GPT 3.5 underperforms:

“We observe that the choice of the evaluator can affect the performance of TAP: changing the attacker from GPT4 to GPT3.5-Turbo reduces the success rate from 84% to 4.2%.

The reason for the reduction in success rate is that GPT3.5-Turbo incorrectly determines that the target model is jailbroken (for the provided goal) and, hence, preemptively stops the method.

As a consequence, the variant sends significantly fewer queries than the original method…”

What This Mean For You

While it’s amusing that the researchers use the ToT method to beat an LLM with another LLM, it also highlights the usefulness of ToT for generating surprising new directions in prompting in order to achieve higher levels of output.

  • TL/DR Takeaways:
  • Tree of Thought prompting outperformed Chain of Thought methods
  • GPT 3.5 worked significantly poorly in comparison to GPT 4 in ToT
  • Pruning is a useful part of a prompting strategy
  • Research showed that ToT is superior to CoT in an intensive reasoning task like jailbreaking an LLM

Read the original research paper:

Tree of Attacks: Jailbreaking Black-Box LLMs Automatically (PDF)

Featured Image by Shutterstock/THE.STUDIO

Source link

Keep an eye on what we are doing
Be the first to get latest updates and exclusive content straight to your email inbox.
We promise not to spam you. You can unsubscribe at any time.
Invalid email address
Continue Reading

Trending