explainx.ainewsletter3.5k
TrendingNewsPathwaysSkills
Pricing
explainx.ai

Upskill in AI — 16 free pathways, live workshops & bootcamps, and 50+ courses from practitioners. Plus the skills, tools, and MCP servers to practice on.

follow us

corporate training

support@explainx.ai

get started

Find your pathTake Free Evaluation

learn

pathways — start freeworkshopsbootcampscoursescertificationsmock testsexplainx universitycorporate traininglearn skills & mcp

discover

skillsmcp serversexplainx mcptoolsagentsllmsdesignsdictionaryagi trackerranks

company

aboutvisionmissionteaminstructorscommunityhackathonscareers

content

daily AI newsstate of AI — live resultsblogreleasespromptsgeneratorsresource libraryfor LLMsexplainx.ai kids

solutions

all solutionsdeveloper upskillingmarketing upskillingproduct manager upskillingleadership upskilling

newsletter · weekly

Get AI news, tools, and insights in your inbox.

supportcontactprivacytermsdata rightshow we create contentsubmission guidelines

© 2026 AISOLO Technologies Pvt Ltd

  1. Home
  2. /
  3. Dictionary
  4. /
  5. Rejection Sampling
Training & Fine-Tuningaka best-of-N sampling

Rejection Sampling

Generating many candidate outputs and keeping only those passing a quality filter.

Ask Melo about this← all terms

Rejection sampling is generating many candidate outputs and keeping only those that pass a quality filter (reward model, verifier, or rule), used both for training data curation and inference-time improvement. This simple but effective technique leverages the observation that model quality varies across samples, and selecting the best yields significantly better results.

Related terms

Reward ModelSynthetic Data GenerationReinforcement Learning from Verifiable RewardsOffline RLCosine AnnealingMulti-Task Learning