{
    "api": "YAML JSON TOON Database",
    "version": "1.0.0",
    "format": "json",
    "dataset": {
        "id": 1651,
        "slug": "rag-retrieval-metrics",
        "title": "Retrieval Evaluation Metrics for RAG",
        "description": "Retrieval metrics and diagnostic slices for evaluating the evidence selected before language-model generation.",
        "summary": "Retrieval metrics and diagnostic slices for evaluating the evidence selected before language-model generation. Each row includes a practical application and a failure to check before using it.",
        "use_when": [
            "Compare retrievers using a fixed judged query set.",
            "Find why an answer lacks evidence before changing the generator."
        ],
        "caveats": [
            "Retrieval quality is separate from answer correctness.",
            "Keep test queries out of retriever tuning and report uncertainty."
        ],
        "related": [
            "llm-evaluation-failure-modes",
            "ml-evaluation-metrics"
        ],
        "reviewed_at": "2026-10-12",
        "sources": [
            {
                "title": "Stanford introduction to information retrieval",
                "url": "https:\/\/nlp.stanford.edu\/IR-book\/html\/htmledition\/evaluation-in-information-retrieval-1.html"
            },
            {
                "title": "Stanford ranked retrieval evaluation",
                "url": "https:\/\/nlp.stanford.edu\/IR-book\/html\/htmledition\/evaluation-of-ranked-retrieval-results-1.html"
            }
        ],
        "reading": [
            "evaluate-rag-retrieval-before-generation"
        ],
        "provenance": "Original editorial reference notes by YJTOON, informed by the linked primary documentation. External specifications retain their own licenses.",
        "entry_count": 10,
        "fields": [
            {
                "section": "data",
                "field": "metric",
                "type": "string",
                "example": "Precision at k"
            },
            {
                "section": "data",
                "field": "definition",
                "type": "string",
                "example": "Relevant retrieved items divided by k."
            },
            {
                "section": "data",
                "field": "use",
                "type": "string",
                "example": "Measure how much top-ranked context is useful."
            },
            {
                "section": "data",
                "field": "limitation",
                "type": "string",
                "example": "It depends on relevance judgments and the chose\u2026"
            }
        ],
        "category": "AI & ML Terms",
        "category_slug": "ai-ml-terms",
        "tags": "ai-ml-terms,rag retrieval metrics,reference,engineering",
        "view_count": 13,
        "created_at": 1791798640,
        "updated_at": 1791798640
    },
    "data": [
        {
            "metric": "Precision at k",
            "definition": "Relevant retrieved items divided by k.",
            "use": "Measure how much top-ranked context is useful.",
            "limitation": "It depends on relevance judgments and the chosen k."
        },
        {
            "metric": "Recall at k",
            "definition": "Relevant retrieved items divided by all known relevant items.",
            "use": "Measure how much required evidence is recovered.",
            "limitation": "Incomplete relevance labels distort the denominator."
        },
        {
            "metric": "Hit rate at k",
            "definition": "Fraction of queries with at least one relevant top-k item.",
            "use": "Check whether the retriever finds any useful evidence.",
            "limitation": "One relevant item can still be insufficient to answer."
        },
        {
            "metric": "Mean reciprocal rank",
            "definition": "Mean of the reciprocal rank of the first relevant result.",
            "use": "Reward finding useful evidence early.",
            "limitation": "It ignores relevant results after the first one."
        },
        {
            "metric": "NDCG at k",
            "definition": "Discounted graded relevance normalized by the ideal ranking.",
            "use": "Compare rankings with multiple relevance grades.",
            "limitation": "Judgment policy and gain function affect scores."
        },
        {
            "metric": "Context coverage",
            "definition": "Fraction of required answer facts supported by retrieved context.",
            "use": "Find multi-document evidence gaps.",
            "limitation": "It requires an explicit set of required facts."
        },
        {
            "metric": "Duplicate rate",
            "definition": "Fraction of retrieved context redundant with other selected items.",
            "use": "Detect wasted context capacity.",
            "limitation": "Overlapping chunks can be useful in some tasks."
        },
        {
            "metric": "Retrieval latency",
            "definition": "Elapsed time for retrieval under a declared load.",
            "use": "Balance evidence quality against responsiveness.",
            "limitation": "Cache state and concurrency change the distribution."
        },
        {
            "metric": "Empty-result rate",
            "definition": "Fraction of queries returning no eligible evidence.",
            "use": "Track abstention and indexing problems.",
            "limitation": "An empty result can be the correct behavior."
        },
        {
            "metric": "Slice performance",
            "definition": "A metric calculated by query or content subgroup.",
            "use": "Expose failures hidden by an overall average.",
            "limitation": "Small slices need uncertainty reporting."
        }
    ]
}