Privilege AIMKC2 results ↗

Held-out evaluation

A held-out set is a consumable resource. Every look at it spends a little, and most evaluation programmes spend it long before they notice.

READ THE DEFINITION ↓SPLITS · LEAKAGE · EXHAUSTION

01 / DEFINITION

The short answer first.

What is held-out evaluation?

Held-out evaluation measures a model on data excluded from every stage of its development: training, prompt iteration, threshold selection and error analysis. The exclusion is what makes the result an estimate of performance on new work rather than a description of what the model has already absorbed.

The definition is simple and the discipline is not. Exclusion has to hold against every channel by which information can reach the model, and in a language model pipeline there are more channels than in classical machine learning: the weights, the prompt, the few-shot examples, the retrieval index, the threshold, and the engineer who has read the failures and adjusted accordingly.

WORKED EXAMPLE

Hold out an incident, not just a row

An engineering team has thousands of maintenance reports from similar machines. One pump failure generates a technician's initial note, a corrected report, a translated copy and a manufacturer's response. A random split can distribute those four documents between training and evaluation. The model may then recognise the incident while appearing to solve a previously unseen diagnosis.

Begin by identifying what should count as an independent unit for the intended deployment. If the system will review new incidents at familiar sites, group the entire incident before splitting. If it must transfer to unfamiliar plants, reserve some plants as well. A valid split depends on the claim you want to make. Neither a random sample nor a time cutoff automatically establishes the right boundary.

Find related material without exposing the final test

Build an incident map from identifiers, equipment references, dates and revision relationships. Inspect uncertain matches on the development side and record your grouping rules. Exact hashes catch identical files but miss translations, paraphrases and reports with a changed cover sheet. Ask an engineer to identify the ordinary document family for one incident and use that example to test the grouping logic.

Freeze the final set and restrict who can inspect its individual labels. Give model developers a separate validation set for prompt changes, threshold selection and adapter tuning. If a developer examines a final failure and changes the model to fix that particular example, move that example into development and arrange fresh confirmation material. Keeping its old label hidden afterward does not undo what the team learned.

Report the independence you actually achieved

Describe how many machines, sites and incidents contribute to the held-out score. An evaluation containing a hundred documents from two independent outages offers different evidence from one containing a hundred separate incidents. Review successes and failures by those units and record whether a particular machine family dominates the result.

When the system is updated, retain the split manifest and the data version. Repeat the comparison against the same incumbent, then obtain a fresh sample for claims about new operating conditions. The resulting record gives a reviewer a concrete answer to a difficult question: what experience could the model or its developers already have had with the material used to justify deployment?

02 / LEAKAGE PATHS

Leakage paths, roughly in order of how often they appear in practice rather than how often they are discussed.
PathWhat happensPractical defence
Prompt iterationThe prompt is tuned until the held-out score improvesA separate development set; the held-out set is read once per decision
Near duplicatesThe same clause or template appears in train and testNear-duplicate detection before splitting, not after
Group leakageDifferent documents from the same matter land on both sidesSplit by matter, client or source, never by row
Temporal leakageTraining data postdates test data, so the future is visibleSplit by date, with the test set strictly later
Pretraining contaminationThe material was public and is already in the base modelPrefer material written after the base model's cut-off
Label reuseThe same annotator labelled both sides with drifting criteriaBlind labelling, with agreement measured separately

Group leakage is the one that produces the largest and most convincing overestimates. Splitting a corpus row by row when rows are clustered by matter, author or template means the model has effectively seen the test items in another form. The score can be dramatically higher than real performance and looks entirely legitimate, because nothing was technically duplicated.

03 / SET EXHAUSTION

Every look
spends a little.

The problem nobody budgets for.

A held-out set used for forty decisions has been optimised against forty times. It has quietly become a development set.

The mechanism is selection, not cheating. Each time a team makes a choice based on the held-out score — a prompt change, a threshold move, a different retrieval depth — it keeps the variant that happened to do better on those particular items. Repeat this often enough and a meaningful part of the reported gain is fitted to the sample.

Three practices keep the problem manageable:

  • A three-way split. Train, development and held-out, with the held-out set read only at acceptance decisions and its use logged.
  • Scheduled rotation. Reserve unlabelled material in advance so a fresh set can be created when the current one has been consumed, rather than scrambling for data after the fact.
  • A recorded read count. If nobody knows how many times the set has been scored, it should be assumed exhausted.

04 / IN PRACTICE

MKC2's published figures come from items that were not seen during training, with 45 separate checks scored on each. Both comparison models — the system being replaced and the stock base model — were re-scored in the same run, on the same items, with the same parser, so the differences reported are differences between models rather than between reports.

The record also states what it does not show. No attorney dispositions have been recorded, so the figures do not demonstrate that MKC2 agrees with a lawyer on live work; they show how it behaves on held-out evaluation data. Keeping that boundary explicit is part of the method, not a disclaimer attached to it. The full record is on the MKC2 page.

HELD-OUT DATA
Train — Develop — Accept
ONE READ PER DECISION

05 / QUESTIONS

What proportion of data should be held out?

Enough for the smallest reported slice to be measurable rather than a fixed percentage. The common 80/10/10 split is a convention, not a requirement; with a large corpus, a smaller fraction is often ample, and with a rare but important class, a stratified sample matters far more than the overall ratio.

How do you detect near duplicates at scale?

Cheap lexical methods first — normalised hashing and shingling catch templates and boilerplate — then embedding similarity for paraphrase. Run detection before splitting and keep duplicate clusters together on one side of the split rather than deleting them, since duplication is often a real property of the domain.

Can a held-out set be reused across model versions?

For a small number of acceptance decisions, yes, and that is exactly what it is for. The risk accumulates with the number of decisions made against it, not with calendar time. Log every read and plan a replacement.

Does held-out evaluation apply to retrieval systems?

Yes, with an extra trap: the retrieval index must not contain the answers to the held-out questions in a form that only exists because those questions were written. Build the index from the production corpus, then draw evaluation questions from material that is genuinely part of it. See RAG evaluation.

What if there is not enough data to hold any out?

Then report cross-validation with confidence intervals and say plainly that no clean acceptance estimate exists. That is a weaker claim, and stating it weakly is better than presenting a development score as an acceptance result.

WORK WITH PRIVILEGE AI

How we can help

Talk with Privilege AI

Describe how your examples were collected and which related records could cross a training or evaluation boundary.

Talk to us →

CONTACT PRIVILEGE AI

Contact Us

Describe how your examples were collected and which related records could cross a training or evaluation boundary.

When should we call?

By submitting, you agree that Privilege AI, a division of Tech1e LLC, may call or email you about this inquiry. Please leave confidential information out of your message.

Build a set
that stays clean.

Privilege AI constructs held-out evaluation sets, detects leakage before it flatters a result, and re-scores every baseline in the same run.