Dr. Patrick Lewis
Cohere
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
Proof of Work
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.
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 missionRetrieval-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.
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