Model evaluation (evals) vs Model training

Why they differ

Training changes the model to fit its examples; evaluation only measures the finished model and must not feed back into it unchecked.

Model evaluation (evals)

Evaluation & metrics

The practice of checking how well an AI system does its job, with scores, public tests, human review and deliberate attacks.

Formal

The planned measuring of a model or AI system against goals for quality, safety and fairness, combining numbers such as accuracy and the F1 score, benchmark results, human review, LLM-as-a-judge grading and AI red teaming.

In plain English

Like a car's road trials before sale, with speed runs on the track, crash checks, drivers' opinions and people trying hard to make it fail.

In practice

Before moving its tenant chat to a newer large language model, a housing association's IT lead reruns 500 saved tenant questions, has staff grade a sample of the answers, and switches only if nothing gets worse.

Why it matters

Without regular checks nobody knows whether a change made the system better, worse or unsafe, and the EU AI Act demands documented testing for systems used in areas such as hiring, credit scoring or welfare decisions.

Model training

Machine learning basics

The costly, one-off stage where a model looks at training data again and again and tunes its internal numbers until its guesses improve.

Formal

The process of repeatedly feeding training data to a model, measuring how far its outputs are from the wanted answers, and adjusting its weights to shrink that gap; the result is a fixed set of learned numbers.

In plain English

Like a darts player throwing thousands of darts, checking how far each lands from the centre, and adjusting their arm a little each time.

In practice

A Danish university books weeks of time at a national computing centre to train a Danish language model once; municipalities and firms that adopt it then only use the finished result.

Why it matters

What happens here decides what the model knows and how it behaves; it is also where poisoned or unlawful data gets built in for good.

Shared connections

Machine learning Test set