---
title: 'Leveraging Passage Retrieval with Generative Models for Open Domain Question Answering'
license: CC-BY-4.0
license_url: https://creativecommons.org/licenses/by/4.0/
license_note: 'paper is arXiv non-exclusive distribution license (verified on arXiv abs page 2026-11-12); this pointer note is our own words and is CC BY 4.0; we link to the paper rather than reproduce it'
source: https://iinventedlight.com/library/notes/2007-01282-fusion-in-decoder.md
source_license: 'arXiv non-exclusive distribution license'
attribution: 'Pointer by iinventedlight (AI-assisted). Source: Gautier Izacard, Edouard Grave, Leveraging Passage Retrieval with Generative Models for Open Domain Question Answering (arXiv non-exclusive distribution license). This note links to the paper rather than reproducing it.'
author: 'iinventedlight (AI-assisted)'
date: 2026-11-12
status: published
approved_by: "Cole Withington, 2026-11-12 14:44 PT, Librarian chat widget t51s316: \"Yes, publish all 100 second-list arXiv notes\""
checked_on: 2026-11-12
as_of: 2026-11-12
confidence: medium
untested: 'Pointer note only. Paper not reproduced. Abs page and license checked 2026-11-12.'
category: arxiv
topic_area: 'ai-research: RAG'
tags: arxiv, RAG, question-answering, generative-models
arxiv_id: 2007.01282
alias: 2007.01282-fusion-in-decoder
type: pointer
format: pointer
sources:
  - id: S1
    title: 'Leveraging Passage Retrieval with Generative Models for Open Domain Question Answering'
    publisher: arXiv
    authors: 'Gautier Izacard, Edouard Grave'
    url: https://arxiv.org/abs/2007.01282
    version_read: 'v2 (3 Feb 2021)'
    accessed: 2026-11-12
    license: 'arXiv non-exclusive distribution license'
---
# Leveraging Passage Retrieval with Generative Models for Open Domain Question Answering

## Summary
[Leveraging Passage Retrieval with Generative Models for Open Domain Question Answering](https://arxiv.org/abs/2007.01282) (2020) introduced Fusion-in-Decoder (FiD), a generative reader that encodes retrieved passages independently and then fuses them in the decoder of a sequence-to-sequence model. It became a standard backbone for retrieval-augmented open-domain question answering.

What it introduced: a way for a generative model to attend over many retrieved passages without concatenating all of them into one expensive encoder sequence, which let the method scale to a large evidence set at answer time.

What it led to: later RAG readers and fusion methods that still follow this encode-separately, fuse-in-the-decoder pattern. Live note: [2005-11401-retrieval-augmented-generation](https://iinventedlight.com/library/notes/2005-11401-retrieval-augmented-generation/). Together with ColBERT in this batch, it covers a classic retrieve-then-generate stack.

Use it when you want the original FiD reader design. Where to read it: https://arxiv.org/abs/2007.01282 (v2 (3 Feb 2021)).

The paper is posted on arXiv under the arXiv non-exclusive distribution license. This note links to it rather than reproducing it. The note itself is CC BY 4.0.

License: this note is CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/). Pointer by iinventedlight (AI-assisted). Paper license: arXiv non-exclusive distribution; this note links to it and does not reproduce it.

---

Agents: [/agents.md](/agents.md) | [/.well-known/agent-library.json](/.well-known/agent-library.json).
