{
 "id": "https://redfinchadvisory.com/lexicon/human-as-judge",
 "slug": "human-as-judge",
 "prefLabel": "Human-as-judge",
 "altLabel": [
  "Human evaluation",
  "Human review",
  "Human rating"
 ],
 "hiddenLabel": [],
 "definition": "An eval where a person reviews a system's output and judges its quality.",
 "scopeNote": "This can be unavoidable when it comes to niche needs like style or preference. Human grades are the standard other judges are checked against, though people often disagree with each other.\nHuman grades are also the starting point to calibrate an LLM-as-judge.",
 "tier": null,
 "group": "Evaluation",
 "broader": [
  "https://redfinchadvisory.com/lexicon/eval"
 ],
 "narrower": [],
 "related": [
  {
   "id": "https://redfinchadvisory.com/lexicon/human-in-the-loop",
   "type": "confused"
  }
 ],
 "links": [
  {
   "id": "https://redfinchadvisory.com/lexicon/llm-as-judge",
   "label": "calibrates",
   "direction": "out"
  }
 ],
 "modified": "2026-10-21",
 "markdown": "https://redfinchadvisory.com/lexicon/human-as-judge.md",
 "inScheme": {
  "id": "https://redfinchadvisory.com/lexicon",
  "version": "1.0",
  "currentAsOf": "2026-10-21"
 }
}