Skip to content
JevDirectory.orgTraffic count unavailable. View site traffic
PrimitivesNone-of-the-above optionOther option

Rejection option

An explicit choice like other or none-of-the-above that gives the model a way to decline, and the reason an option list without one can only pick the least-wrong answer.

All 172 terms
Category
Primitives
Also known as
None-of-the-above option, Other option
Related terms
4
Directory entries
4
Docs
—
Added
2026-10-14

Definition

A Choice can only return one of the options it was given, so a candidate set with no valid answer forces a guess unless the question includes a rejection option. TypeSafe's guidance is to add an other or none-of-the-above choice whenever the list may not cover the input, and to treat the probability on that option as the abstention signal your code gates on.

Rejection behavior is weaker than it looks. On paired arithmetic problems with an explicit rejection option, answer-present accuracy reached 99% while correct rejection fell to 7%, even though the same model verified candidate correctness at 99% when asked as a Noul — a decision threshold selected on separate development problems raised rejection to 79% while keeping 97% answer-present accuracy. Test rejection on inputs you know are out of scope, not only on covered ones.

Tagsprimitiveschoiceconfidence

Related terms

Definitions that connect to this one.

ChoicePick one option from a set you define; returns the selected option, a probability for every option, and confidence.PrimitivesChoice optionOne key in a Choice criteria map, with a description that can be a string, a structured object, or null.PrimitivesNull criteriaPassing null as a Choice option description when the option name needs no extra explanation.PrimitivesConfidence floorA baseline below which code never acts on an answer, regardless of what the answer says.Answers & Confidence

From the Jev directory

When the Right Answer Is Missing: An Arithmetic-Dependent Rejection Bottleneck in Jev (arXiv 2609.39496)
A report identifying an arithmetic-dependent rejection bottleneck in Jev: on paired arithmetic problems answer-present accuracy reaches 99% while correct rejection falls to 7%. A development-selected decision threshold lifts rejection from 7% to 79% while retaining 97% answer-present accuracy.
Jev Practices & PatternsArticle#community#research#arxiv
Community
Benchmarking candidate coverage and rejection policy transfer in typed decision models (arXiv 2610.03387)
0GitHub stars
A benchmark of rejection-policy transfer across Laya, Jev, and Qwen2.5-7B-Instruct at equal calibration budgets, covering artificial omission, natural retrieval misses, and public out-of-scope queries. Source calibration often fails to preserve the target operating point.
Jev Benchmarks & EvaluationsArticle#community#research#arxiv
Communityluckykevvv/Decision_Model_BenchmarkPython
Does a Hosted Decision Model Respect Irrelevant Alternatives? A Pre-Registered Test of Option-Set Dependence in Jev (arXiv 2610.16655)
A pre-registered study of whether jev-1.13.0 satisfies independence of irrelevant alternatives, using 299,463 calls on intent and topic classification. Every added option shifts the log-odds between the gold and strongest wrong label by 0.20–0.52 nats RMS, 1.2 to 3 times run-to-run variation.
Jev Benchmarks & EvaluationsArticle#community#research#arxiv
Community
Choice
Pick one option from a set you define. Returns the option, the full probability distribution, and 0-1 confidence, with up to 255 options and parallel questions that barely add latency.
Jev Practices & PatternsDocs#official#primitives#choice
Official

From the Jev community

Posts from builders shipping with Jev right now.

Follow @typesafeai