Karpukhin et al.: dense dual-encoder passage retrieval for open QA

What changed

Trained independent question and passage encoders from question-passage supervision and used dense similarity retrieval to supply evidence for an open-domain answer reader.

Scientific scope

Trained independent question and passage encoders from question-passage supervision and used dense similarity retrieval to supply evidence for an open-domain answer reader. Dual encoders, dense similarity and BERT pretraining are inherited. Retrieval relevance is not answer truth, and dense retrieval does not universally dominate sparse BM25.

Evidence

The linked original sources describe the stated contribution and its evidence limits. WRS has not independently rerun the experiments or certified a proof. Dual encoders, dense similarity and BERT pretraining are inherited. Retrieval relevance is not answer truth, and dense retrieval does not universally dominate sparse BM25.

Contributors

• Source-listed authors and technical contributors · SCIENCE: Source-listed authors or explicitly credited technical contributors for the cited versions. Family entries retain source-specific attribution; a combined list is not one original-paper byline or equal individual work. Names alone do not establish resolved identities.

• Dense Passage Retrieval for Open-Domain Question Answering
• Karpukhin et al.: dense dual-encoder passage retrieval for open QA — original project

Provisional WRS assessment, edition 2026-10-16.1. Independent expert calibration is pending. This grade does not certify correctness or assign ownership.

Full scientific record · Browse contribution grades · Request a correction