Skip to content

The four types of AI data tasks, explained

Pathwize EditorialExpert data and AI evaluation3 min read
GuidesPathwize AI

Preference, evaluation, red teaming and domain judgment. What each task type does, when to use it, and how they fit together in a data programme.

Most human data work falls into a handful of shapes. Once you can name them, planning a data programme gets a lot easier, because each shape answers a different question about your model. On Pathwize you create work as one of four task types: RLHF / Preference, Evaluation / Grading, Red teaming, and Domain judgment / SFT. This guide explains what each one is for and how to combine them.

1. Preference (RLHF)

In a preference task, an expert sees two model outputs for the same prompt and picks the better one, with a short rationale. The output is a comparison, not a score. This is the raw material for reward models and RLHF: you are teaching the model what humans prefer, one pairwise judgment at a time.

Reach for preference tasks when quality is comparative rather than absolute, when two answers can both be defensible and you want the model to learn the tie-breakers a good expert applies.

2. Evaluation (grading)

An evaluation task scores a single output against a rubric, either pass/fail or on a scale. The rubric is the whole game: it turns a vague sense of quality into a repeatable measurement that different graders apply the same way.

Use evaluation when you need a number you can track over time, a benchmark for a release, a regression check, or a quality gate. Preference tells you which is better; evaluation tells you how good, against a fixed standard.

3. Red teaming

Red teaming asks experts to probe the model for failures: jailbreaks, unsafe outputs, and the edges where it breaks. The goal is not to grade normal behaviour but to find the inputs that produce bad behaviour, and to document how.

Use it before a release, whenever you ship a capability that could be misused, and as an ongoing safety practice. The deliverable is a set of reproducible failure cases, which feed both your safety evaluations and your fixes.

4. Domain judgment (SFT)

Here the expert writes the ideal answer, or the authoritative judgment, for each item. This is supervised fine-tuning data at its source: not a comparison and not a score, but the gold response itself, authored by someone qualified to produce it.

Use domain judgment when the model needs to learn from correct examples in a specialised field (medicine, law, frontier maths, security) and only a credentialed expert can say what correct looks like.

How they fit together

A mature programme uses all four. Domain judgment builds the gold set the model learns from. Preference tunes its behaviour toward what experts favour. Evaluation measures whether any of it worked. Red teaming stress-tests the result before it ships. They are stages in a loop, not competing options.

The thread that runs through all four is the same one behind everything we build: every judgment should carry a signed, reproducible trail, so you can prove who produced it and under what instructions. Pick the task type that answers your question, and keep the provenance whichever you choose.

Frequently asked questions

What are the main types of AI data tasks?+

Four cover most work: preference (RLHF), where experts compare two outputs and pick the better one; evaluation or grading, where outputs are scored against a rubric; red teaming, where experts probe for failures and unsafe behaviour; and domain judgment (SFT), where experts write the ideal answer for each item.

What is the difference between preference and evaluation tasks?+

Preference is comparative: an expert picks the better of two outputs. Evaluation is absolute: an output is scored against a fixed rubric. Preference tells you which is better, evaluation tells you how good against a standard.

Do I need all four task types?+

Not to start, but a mature programme tends to use all four as stages in a loop: domain judgment builds the gold set, preference tunes behaviour, evaluation measures quality, and red teaming stress-tests before release.

Related reading

See Pathwize on your own data

Source verifiable expert data with provenance built in, EU-native and audit-ready.

Book a demo
← All posts

Related stories

GuidesPathwize AI

How to evaluate an AI data vendor: a due-diligence checklist

The questions that separate a data vendor you can defend to an auditor from one that will cost you a re-labelling project six months in.

Pathwize AIGuides

How to run a human-data pilot before you commit

A pilot is the cheapest way to learn whether a data partner can actually do your hardest work. Here is how to design one that tells you something real.

InsightPathwize AI
Guides

Preference and RLHF tasks: teaching a model what good looks like

Pairwise comparison is the workhorse of RLHF. How preference tasks work, why the rationale matters as much as the choice, and how to design them well.