CERTALYXCERTIFICATION REGISTRY
CoursesPricingStandardVerificationLegal
Sign inStart free

Catalogue

Model Evaluation & RLHF

Judgement work: preference ranking, hallucination, bias and multi-turn review.

All 24Data Annotation & Labeling · $25Prompt Engineering & LLM · $99Model Evaluation & RLHF · $99Domain-Specific Evaluation · $249
Model Evaluation & RLHFIntermediate

RLHF Preference Ranking

Ranking model responses on a rubric, including ties, honesty and rater agreement.

3 modules4h$99
Model Evaluation & RLHFIntermediate

Hallucination Detection

Separating fluent invention from grounded fact and rating severity.

3 modules3h$99
Model Evaluation & RLHFIntermediate

Bias & Toxicity Testing

Testing identity-targeted harm, stereotype endorsement and context-dependent toxicity.

3 modules4h$99
Model Evaluation & RLHFIntermediate

A/B Model Comparison

Blind pairwise comparison with order, length and formatting bias controlled.

3 modules3h$99
Model Evaluation & RLHFBeginner

Helpfulness Scoring

Scoring task completion and instruction following, including partial credit.

3 modules2h$99
Model Evaluation & RLHFExpert

Multi-Turn Evaluation

Judging conversations where the failure only appears across several turns.

3 modules5h$99

CERTALYX

Certalyx issues signed, registry-backed certificates for practical AI work. Independent, signed and verifiable by ID.

Established 2026. Registry enquiries: registry@certalyx.com

Programme

  • Course catalogue
  • How certification works
  • Verify a certificate
  • Learner dashboard

Legal

  • Terms & refunds
  • Privacy
  • Credential statement
  • Verification public key

Certalyx is an independent training and credentialing body. A Certalyx certificate evidences completion and assessment under the Certalyx syllabus. It is not a government licence, and it does not by itself confer any right to practise a regulated profession.