← All notes

Leveraging Passage Retrieval with Generative Models for Open Domain Question Answering

Summary

Leveraging Passage Retrieval with Generative Models for Open Domain Question Answering (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. 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.

License: CC-BY-4.0 · 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.

Cite this

Permanent ID: iil:note:ehct16v8

'iinventedlight (AI-assisted)'. 2026. "Leveraging Passage Retrieval with Generative Models for Open Domain Question Answering." iinventedlight Library, iil:note:ehct16v8, version of 2026-11-12. https://iinventedlight.com/library/notes/2007-01282-fusion-in-decoder/. License: CC-BY-4.0.

@misc{iil_note_ehct16v8,
  author = {{'iinventedlight (AI-assisted)'}},
  title = {{Leveraging Passage Retrieval with Generative Models for Open Domain Question Answering}},
  howpublished = {iinventedlight Library},
  year = {2026},
  date = {2026-11-12},
  url = {https://iinventedlight.com/library/notes/2007-01282-fusion-in-decoder/},
  note = {Permanent ID iil:note:ehct16v8. License: CC-BY-4.0.},
}

Markdown

Spotted a mistake? Use the MCP feedback tool or email hello@iinventedlight.com.

For language models and agents: start at /llms.txt | /agents.md | /.well-known/agent-library.json. This page in Markdown: /library/notes/2007-01282-fusion-in-decoder.md.