If- every- test- case- in- your- set- is- easy,- the- set- will- not- catch- the- regressions- that- matter.- Include- at- least- 20%- of- cases- where- the- correct- answer- is- "I- don't- know,"- "not- enough- evidence,"- or- a- refusal.- A- model- that- answers- everything- confidently- will- look- good- on- easy- cases- and- fail- silently- on- the- hard- ones.

##- TL;DR

If- your- LLM- output- matters- to- users,- keep- a- small- regression- set- that- you- can- run- after- prompt,- model- or- retrieval- changes.

The- set- should- include- real- user- tasks,- known- hard- cases- and- examples- where- the- correct- answer- is- “I- do- not- know”- or- “not- enough- evidence”.- That- makes- it- harder- for- a- shiny- new- model- to- look- better- than- it- is.

##- What- belongs- in- the- set

A- useful- small- set- usually- includes:

common,- ordinary- user- questions; edge- cases- that- have- failed- before; prompts- that- tempt- the- model- to- guess; prompts- with- missing- context; prompts- where- refusal- or- uncertainty- is- the- correct- outcome; prompts- that- need- grounding- in- a- source,- policy- or- database- record.

If- every- test- case- is- easy,- the- set- will- not- catch- the- regressions- that- matter.

##- How- to- build- it

A- practical- build- process- looks- like- this:

1.- collect- real- examples- from- support,- logs- or- product- reviews; 2.- remove- sensitive- data; 3.- write- the- expected- answer- or- expected- behaviour; 4.- mark- which- source- or- rule- the- answer- depends- on; 5.- decide- what- counts- as- a- pass,- a- partial- pass- or- a- fail; 6.- keep- the- set- small- enough- that- people- will- actually- run- it.

A- tiny- set- that- is- used- regularly- beats- a- huge- set- that- sits- untouched.

##- What- to- watch- for

Hallucination- testing- should- catch- more- than- obvious- factual- errors.

Watch- for:

invented- details; unsupported- certainty; mixing- up- similar- entities- or- dates; missing- citations- or- source- drift; unsafe- advice- where- caution- was- required; confident- answers- to- underspecified- prompts.

A- model- can- sound- polished- while- still- being- wrong.- The- test- set- should- reward- correctness,- not- confidence.

##- A- simple- pass- metric

One- useful- planning- metric- is:

Pass- rate- =- supported- responses- /- total- test- cases

That- number- is- only- useful- if- the- test- cases- are- stable- and- the- pass- criteria- are- written- down.- Otherwise- the- score- becomes- theatre- —- the- same- risk- that- makes- LLM-as-a-judge- grading- unreliable- without- a- written- rubric.

Treat- the- metric- as- a- trend,- not- a- verdict.

##- Practical- decision- check

Before- you- rely- on- a- regression- set,- ask:

Are- these- real- tasks- or- toy- examples? Do- we- have- a- written- pass/fail- rule? Are- the- hardest- cases- actually- represented? Can- the- set- catch- the- failure- modes- we- care- about? Will- the- team- run- it- after- changes? Is- there- a- human- review- path- for- uncertain- cases?

If- the- answer- to- any- of- those- is- no,- the- set- is- probably- too- weak.