← Search

Radu Revutchi

1 accepted papers

2026

Coverage, Not Averages: Semantic Stratification for Trustworthy Retrieval Evaluation

ICML 2026poster

Retrieval quality is the primary bottleneck for accuracy and robustness in retrieval-augmented generation (RAG). Current evaluation relies on heuristically constructed query sets, which introduce a hidden intrinsic bias. We formalize retrieval evaluation as a statistical estimation problem, showing …

Cited by 0SourceScholar