Dr. Patrick Lewis

Cohere

Sources checked
ABOUT

Research Lead at Cohere and former AI Research Scientist at Meta AI. Lead author of the seminal 2020 paper 'Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks', which created the RAG paradigm combining dense vector retrievers with parametric sequence-to-sequence foundation models.

Areas of focus

Professional niches

THE WORK BEHIND THE PROFILE

Proof of Work

researchChecked Sep 21, 2026

KILT: Benchmarking Knowledge Intensive Language Tasks for Grounded Generation

Developed the KILT benchmark standardizing evaluation across open-domain QA, fact checking, entity linking, and dialogue, measuring both answer generation accuracy and provenance attribution.

Scope & limitations

Corpus snapshot drift requires periodic index refreshes to keep knowledge-intensive models updated with real-world facts.

Context: Unified Wikipedia corpus snapshot with passage-level attribution targets.

View mission
researchChecked Sep 21, 2026

Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks

Authored the foundational NeurIPS 2020 paper defining Retrieval-Augmented Generation (RAG), introducing end-to-end differentiable architectures that ground generative models against external non-parametric neural indices.

Scope & limitations

Early RAG formulated single-step retrieval; complex multi-hop reasoning requires iterative or agentic retrieval loops.

Context: DPR (Dense Passage Retriever) coupled with BART sequence-to-sequence generation over Wikipedia index.

View mission

Guides to evaluating AI expertise