Skip to content

Retrieval-Augmented Generation (RAG)

Definition
AI-generated

Retrieval-augmented generation couples a language model with a retriever over a document corpus (papers, manuals, database snippets) so that answers are conditioned on fetched evidence, reducing reliance on parametric memory alone.

Topics
LLM and Agents
Synonyms
RAG
Related
FAIR Principles Large Language Model (LLM) LLM Hallucination

Why it matters in GWAS

RAG-style pipelines can ground responses in local PDFs, methods supplements, or curated variant databases; retrieval quality and chunking still determine whether answers stay faithful to the cited sources.

Example usage

"We built a RAG index over the lab’s SOPs and GWAS QC wiki so the assistant could cite paragraph-level excerpts when answering trainee questions."

FAIR Principles Large Language Model (LLM) LLM Hallucination Prompt Engineering
Related-term network

Click any node to open that term page.

Node order. The current term is first. Next come every page linked from Related terms, in the same top-to-bottom order as that list. Then new terms appear in two-hop layers: for each of those direct neighbors (in that same order), their related terms are appended if not already listed. A third pass does the same for two-hop nodes. The walk stops when a fixed maximum number of nodes is reached.

References

  • Lewis P, et al. (2020). Retrieval-augmented generation for knowledge-intensive NLP tasks. NeurIPS.
← Restriction site Retrospective cohort →

Last updated (UTC · Git history)