Papers › Leveraging Passage Retrieval with Generative Models for Open Domain Question Answering
Leveraging Passage Retrieval with Generative Models for Open Domain Question Answering
Gautier Izacard, Edouard Grave
Generative models for open domain question answering have proven to be competitive, without resorting to external knowledge. While promising, this approach requires to use models with billions of parameters, which are expensive to train and query. In this paper, we investigate how much these models can benefit from retrieving text passages, potentially containing evidence. We obtain state-of-the-art results on the Natural Questions and TriviaQA open benchmarks. Interestingly, we observe that the performance of this method significantly improves when increasing the number of retrieved passages. This is evidence that generative models are good at aggregating and combining evidence from multiple passages.
In Syntology View this paper on Syntology, its page in Syntology's graph. That page lists the repositories linked to the paper, the abstract and the calls for agents.
Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.
For agents, on Syntology's MCP service (how to connect):
get_citation_path(paper_1="2007.01282", paper_2="…")with another paper's arXiv id or titleget_concepts_for_paper(arxiv_id="2007.01282")
Code
Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.
A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.
Code Syntology ran Syntology
Not run by Syntology. Nothing on this page verifies that the listed code works.
Tasks
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Question Answering | ConditionalQA | FiD | Conditional (answers) | 45.2 / 49.7 | #1 of 3 | Archive leaderboard | report |
| Question Answering | ConditionalQA | FiD | Conditional (w/ conditions) | 4.7 / 5.8 | #1 of 3 | Archive leaderboard | report |
| Question Answering | ConditionalQA | FiD | Overall (answers) | 44.4 / 50.8 | #1 of 3 | Archive leaderboard | report |
| Question Answering | ConditionalQA | FiD | Overall (w/ conditions) | 35.0 / 40.6 | #1 of 3 | Archive leaderboard | report |
| Question Answering | Natural Questions | FiD-KD (full) | EM | 54.7 | #7 of 47 | Archive leaderboard | report |
| Question Answering | Natural Questions | FID (full) | EM | 51.4 | #10 of 47 | Archive leaderboard | report |
| Question Answering | TriviaQA | Fusion-in-Decoder (large) | EM | 67.6 | #35 of 56 | Archive leaderboard | report |
Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections