Can computers really mark exams? Benefits of ELT automated assessments

ɫèAV Languages
Hands typing at a laptop with symbols

Automated assessment, including the use of Artificial Intelligence (AI), is one of the latest education tech solutions. It speeds up exam marking times, removes human biases, and is as accurate and at least as reliable as human examiners. As innovations go, this one is a real game-changer for teachers and students. 

However, it has understandably been met with many questions and sometimes skepticism in the ELT community – can computers really mark speaking and writing exams accurately? 

The answer is a resounding yes. Students from all parts of the world already take AI-graded tests.  aԻ Versanttests – for example – provide unbiased, fair and fast automated scoring for speaking and writing exams – irrespective of where the test takers live, or what their accent or gender is. 

This article will explain the main processes involved in AI automated scoring and make the point that AI technologies are built on the foundations of consistent expert human judgments. So, let’s clear up the confusion around automated scoring and AI and look into how it can help teachers and students alike. 

AI versus traditional automated scoring

First of all, let’s distinguish between traditional automated scoring and AI. When we talk about automated scoring, generally, we mean scoring items that are either multiple-choice or cloze items. You may have to reorder sentences, choose from a drop-down list, insert a missing word- that sort of thing. These question types are designed to test particular skills and automated scoring ensures that they can be marked quickly and accurately every time.

While automatically scored items like these can be used to assess receptive skills such as listening and reading comprehension, they cannot mark the productive skills of writing and speaking. Every student's response in writing and speaking items will be different, so how can computers mark them?

This is where AI comes in. 

We hear a lot about how AI is increasingly being used in areas where there is a need to deal with large amounts of unstructured data, effectively and 100% accurately – like in medical diagnostics, for example. In language testing, AI uses specialized computer software to grade written and oral tests. 

How AI is used to score speaking exams

The first step is to build an acoustic model for each language that can recognize speech and convert it into waveforms and text. While this technology used to be very unusual, most of our smartphones can do this now. 

These acoustic models are then trained to score every single prompt or item on a test. We do this by using human expert raters to score the items first, using double marking. They score hundreds of oral responses for each item, and these ‘Standards’ are then used to train the engine. 

Next, we validate the trained engine by feeding in many more human-marked items, and check that the machine scores are very highly correlated to the human scores. If this doesn’t happen for any item, we remove it, as it must match the standard set by human markers. We expect a correlation of between .95-.99. That means that tests will be marked between 95-99% exactly the same as human-marked samples. 

This is incredibly high compared to the reliability of human-marked speaking tests. In essence, we use a group of highly expert human raters to train the AI engine, and then their standard is replicated time after time.  

How AI is used to score writing exams

Our AI writing scoring uses a technology called . LSA is a natural language processing technique that can analyze and score writing, based on the meaning behind words – and not just their superficial characteristics. 

Similarly to our speech recognition acoustic models, we first establish a language-specific text recognition model. We feed a large amount of text into the system, and LSA uses artificial intelligence to learn the patterns of how words relate to each other and are used in, for example, the English language. 

Once the language model has been established, we train the engine to score every written item on a test. As in speaking items, we do this by using human expert raters to score the items first, using double marking. They score many hundreds of written responses for each item, and these ‘Standards’ are then used to train the engine. We then validate the trained engine by feeding in many more human-marked items, and check that the machine scores are very highly correlated to the human scores. 

The benchmark is always the expert human scores. If our AI system doesn’t closely match the scores given by human markers, we remove the item, as it is essential to match the standard set by human markers.

AI’s ability to mark multiple traits 

One of the challenges human markers face in scoring speaking and written items is assessing many traits on a single item. For example, when assessing and scoring speaking, they may need to give separate scores for content, fluency and pronunciation. 

In written responses, markers may need to score a piece of writing for vocabulary, style and grammar. Effectively, they may need to mark every single item at least three times, maybe more. However, once we have trained the AI systems on every trait score in speaking and writing, they can then mark items on any number of traits instantaneously – and without error. 

AI’s lack of bias

A fundamental premise for any test is that no advantage or disadvantage should be given to any candidate. In other words, there should be no positive or negative bias. This can be very difficult to achieve in human-marked speaking and written assessments. In fact, candidates often feel they may have received a different score if someone else had heard them or read their work.

Our AI systems eradicate the issue of bias. This is done by ensuring our speaking and writing AI systems are trained on an extensive range of human accents and writing types. 

We don’t want perfect native-speaking accents or writing styles to train our engines. We use representative non-native samples from across the world. When we initially set up our AI systems for speaking and writing scoring, we trialed our items and trained our engines using millions of student responses. We continue to do this now as new items are developed.

The benefits of AI automated assessment

There is nothing wrong with hand-marking homework tests and exams. In fact, it is essential for teachers to get to know their students and provide personal feedback and advice. However, manually correcting hundreds of tests, daily or weekly, can be repetitive, time-consuming, not always reliable and takes time away from working alongside students in the classroom. The use of AI in formative and summative assessments can increase assessed practice time for students and reduce the marking load for teachers.

Language learning takes time, lots of time to progress to high levels of proficiency. The blended use of AI can:

  • address the increasing importance of formative assessmentto drive personalized learning and diagnostic assessment feedback 

  • allow students to practice and get instant feedback inside and outside of allocated teaching time

  • address the issue of teacher workload

  • create a virtuous combination between humans and machines, taking advantage of what humans do best and what machines do best. 

  • provide fair, fast and unbiased summative assessment scores in high-stakes testing.

We hope this article has answered a few burning questions about how AI is used to assess speaking and writing in our language tests. An interesting quote from Fei-Fei Li, Chief scientist at Google and Stanford Professor describes AI like this:

“I often tell my students not to be misled by the name ‘artificial intelligence’ — there is nothing artificial about it; A.I. is made by humans, intended to behave [like] humans and, ultimately, to impact human lives and human society.”

AI in formative and summative assessments will never replace the role of teachers. AI will support teachers, provide endless opportunities for students to improve, and provide a solution to slow, unreliable and often unfair high-stakes assessments.

Examples of AI assessments in ELT

At ɫèAV, we have developed a range of assessments using AI technology.

Versant

The Versant tests are a great tool to help establish language proficiency benchmarks in any school, organization or business. They are specifically designed for placement tests to determine the appropriate level for the learner.

PTE Academic

The  is aimed at those who need to prove their level of English for a university place, a job or a visa. It uses AI to score tests and results are available within five days. 

Read more about the use of AI in our learning and testing here.

Explore our courseware and exams

More blogs from ɫèAV

  • A person in a white hoodie sits at a desk, working on a laptop, with bookshelves in the background.

    How to support weaker learners remotely in language classes

    By
    Reading time: 4 minutes

    Language teachers know that remote teaching accentuates differences within a class. Students who need more time, repetition and reassurance can feel lost – unless we intentionally design for them. This guide explains how to support weaker learners online, assist struggling students remotely, and help language students who find classes difficult, all without slowing down the rest of the students. Using clear routines, inclusive online teaching and the right tools, you can create virtual classrooms where confidence and progress grow for every learner.

    Start with clarity and differentiation in online language teaching

    Differentiation in online language teaching begins with a precise understanding of all your students' needs.

    • Run brief skill checks at the start of each unit (listening, reading, vocabulary, grammar); a handful of well-targeted items reveals where weaker learners need focus.
    • Map access and conditions. Ask about device type, bandwidth and study environment to plan contingencies for low-tech days.
    • Set one micro-goal per learner per week (for example, “Use three new adjectives to describe a photo.”). Small, specific goals keep momentum.

    Remote teaching strategies for mixed-ability classes

    Mixed ability is the norm online. Structure your lessons to reduce cognitive load and keep every learner engaged; again this helps support struggling learners.

    • Use a predictable flow: Connect (review and warm-up) > Input (listening/reading) > Focus (language noticing) > Practice (guided) > Use (communicative) > Reflect (self-check).

    Offer "must / should / could" pathways:

    • Must secure essential outcomes for all learners
    • Should consolidate skills for those ready to go further
    • Could stretch confident learners without overwhelming others

    Keep tasks short (5–8 minutes) and signal the mode clearly (listen, read, speak, write).

    Scaffolding techniques for online language learning

    Weaker learners thrive on intentional scaffolds that lower barriers and build independence.

    Listening

    • Pre-teach a handful of key words with visuals or quick gestures.
    • Play audio in short chunks with a single purpose each time: gist, detail, then language noticing.
    • Reveal transcripts only after the second listen to confirm understanding, not replace it.

    Reading

    • Set a clear purpose (“Find two reasons the writer gives for…”) before reading.
    • Provide mini glossaries and encourage highlights and margin notes.
    • Model skimming and scanning strategies with a quick think-aloud.

    Speaking

    • Share sentence frames and functional language (“I agree because…”, “Could you clarify…?”).
    • Give rehearsal time with private voice notes before live speaking.
    • Use small groups with roles (timekeeper, summarizer, supporter) and prompt cards.

    Writing

    • Co-construct a model paragraph, then move to guided writing with checklists and word banks.
    • Encourage drafting and redrafting with a single improvement focus (for example, verb endings).

    Online ESL support strategies like these are included in many tasks, making it easier to scaffold without reinventing materials.

    How to engage weaker learners during online lessons

    Engagement is a design choice. Create multiple entry points and safe participation.

    • Offer varied response modes: chat, polls, reactions and voice. Let learners choose their on-ramp.
    • Structure breakout rooms intentionally. Pair confident learners with developing ones, share clear prompts and keep instructions visible.
    • Visit rooms to coach, not catch. Praise specific behaviors (“Nice turn-taking and great use of follow-up questions.”).

    Inclusive teaching online is about psychological safety. Normalize effort and mistakes: “Thanks for trying that structure – let’s polish it together.”

    Ways to motivate struggling students in virtual classrooms

    Students are most motivated when their progress is visible and they receive constructive, concise feedback.

    • Use quick, auto-graded practice for instant wins on accuracy.
    • Keep teacher feedback focused: one or two points per task, delivered as short audio/video notes when possible.
    • Allow resubmission with a success criterion (“Record again aiming for clearer word endings.”).
    • Celebrate micro-achievements publicly (with consent) and privately to build self-belief.

    Tips for supporting mixed-ability groups online

    Build independence with targeted asynchronous supports.

    • Post short screencasts (under five minutes) explaining tricky points.
    • Share downloadable task cards or checklists for low-bandwidth days.
    • Encourage weekly learning logs: What I tried, What worked, What I’ll try next.
    • Use spaced repetition through assignable mobile practice.

    How to adapt language lessons for different levels online

    Planning for multiple levels is easier when you think in layers.

    • Layer input: same topic, different text/audio lengths and complexity.
    • Layer support: word banks, sentence frames and visuals for those who need more; open prompts for advanced learners.
    • Layer outcomes: all learners meet the core objective; confident learners add a twist (for example, an extra opinion or example).

    How to help low-level students in online classes

    • Keep instructions concise and consistent. One slide = one task.
    • Model, then co-construct before independent work.
    • Use strategically: allow brainstorming in the first language, then pivot to English for performance.
    • Provide accessible materials: readable fonts, captions, transcripts and mobile-friendly tasks.

    Supporting your remote learners is both an art and a system. When you design with clarity, scaffold intentionally, and use the right digital supports, you can support weaker students remotely and online, as well as support struggling learners in language classes with confidence.

  • Teaching with purpose: Why the GSE still works in 2025

    By
    Reading time: 5 minutes

    We live in a world in which change is a constant. While change has always existed, lately it has definitely accelerated. There is an idea in society that we should embrace change and adopt whatever is new, with an underlying assumption – wrong to many – that what is new is always better.one that is often wrong

    In the world of ELT, new materials are developed every year. It is unthinkable for most teachers to be using teaching materials that were published 10 years ago. Some would even claim that anything published before 2020 is already out-dated.

    How does all this impact on the Global Scale of English (GSE) – published over 10 years ago? When it was launched in 2014, it constituted a significant innovation in ELT. The following quotes were provided by ELT experts at the time of launch.

  • Three individuals are engaged in a discussion around a table in a library, surrounded by books, with one person gesturing with their hands.

    Ready to study in the USA? Not all tests are created equal

    By
    Reading time: 2 minutes

    If you’re planning to study in the USA, you’ve probably looked into English proficiency tests for university admissions. And you’ve probably noticed – they’re not all the same.

    • Some are more expensive.
    • Some take weeks to deliver results.
    • Some require you to travel to a test centre.

    The ɫèAV English Express Test is different.

    What makes the ɫèAV English Express Test special?

    This online English test is designed for international students who want to move quickly and confidently through the admissions process.

    • Take it from home– No travel needed. The ɫèAV English Express Test is fully online, so you can complete your exam from anywhere in the world.
    • Get certified results in 48 hours– No long waits. Receive your official English proficiency scores fast, so you can meet university deadlines with ease.
    • Pay less– It’s one of the most affordable English tests for US university applications, helping you save on costs.
    • Accepted by a growing number of US universities– Use your results to apply to top institutions across the United States.
    • Built for momentum, not delays– Designed to help you move forward, not slow you down.

    Why this test matters

    When you’re applying to study in the USA, every day counts. You’re juggling application deadlines, coordinating with universities and planning your next big move. You need an English language test that supports your ambitions, not one that holds you back.

    What makesɫèAV English Express Test different?

    • AI scoring for fairness and consistency– Advanced technology ensures your results are accurate and impartial.
    • Security inbuilt– Take your test with confidence, knowing your identity and results are protected.
    • CEFR and GSE-aligned results– Trusted by universities and colleges, your scores are mapped to international standards for English proficiency.

    It’s everything you need for your US university application, without the stress.

    Ready to take the test?

    If you’re searching for an English proficiency test that fits into your life and helps you move forward, the ɫèAV English Express Test is ready when you are. Take your test today and start your journey to studying in the USA with confidence.