Skip to content

Latest commit

 

History

History
28 lines (23 loc) · 1.21 KB

File metadata and controls

28 lines (23 loc) · 1.21 KB

Evaluation Dataset

questions.json is a JSON list of evaluation samples:

{
  "question": "What does the faithfulness metric measure?",
  "ground_truth": "Faithfulness measures the fraction of claims in the answer supported by the retrieved context; a low score indicates hallucination.",
  "expected_doc_ids": ["rag_evaluation"]
}
Field Required Used by
question yes everything
ground_truth yes context recall (LLM judge)
expected_doc_ids no hit rate & MRR (deterministic). File stem(s) of the corpus document(s) containing the answer. Omit if unknown — the sample is then skipped for these two metrics.

Tips for writing good eval questions

  • Cover every corpus document with at least one question, otherwise the benchmark cannot detect retrieval blind spots.
  • Mix paraphrase questions (test dense retrieval) with exact-term questions containing rare tokens like acronyms (test BM25 / hybrid).
  • Include at least one unanswerable question if you want to test that the generator refuses instead of hallucinating.
  • 30+ questions make LLM-judged metric differences meaningful; the included 10 are a starter set for the sample corpus.