Papers › Improving Passage Retrieval with Zero-Shot Question Generation

Improving Passage Retrieval with Zero-Shot Question Generation

15 Apr 2022arXiv:2204.07496archive 2025-07-28

Devendra Singh Sachan, Mike Lewis, Mandar Joshi, Armen Aghajanyan, Wen-tau Yih, Joelle Pineau, Luke Zettlemoyer

We propose a simple and effective re-ranking method for improving passage retrieval in open question answering. The re-ranker re-scores retrieved passages with a zero-shot question generation model, which uses a pre-trained language model to compute the probability of the input question conditioned on a retrieved passage. This approach can be applied on top of any retrieval method (e.g. neural or keyword-based), does not require any domain- or task-specific training (and therefore is expected to generalize better to data distribution shifts), and provides rich cross-attention between query and passage (i.e. it must explain every token in the question). When evaluated on a number of open-domain retrieval datasets, our re-ranker improves strong unsupervised retrieval models by 6%-18% absolute and strong supervised models by up to 12% in terms of top-20 passage retrieval accuracy. We also obtain new state-of-the-art results on full open-domain question answering by simply adding the new re-ranker to existing models with no further changes.

PaperPDFCodeCode Syntology ranMethod as code

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also 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):

Code

Syntology 14 code samples harvested from 2 repositories linked to this paper: 8 ran (of which 4 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 3 where Syntology's instrument failed) · 6 unverified. Where Syntology's instrument failed: 3 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 10 samples from 1 repository, 8 ran (5 with no instrument failure; 3 where Syntology's instrument failed); found in paper text by Syntology: 4 samples from 1 repository, 0 ran (0 with no instrument failure; 0 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written on 2026-09-22 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

DevSinghSachan/unsupervised-passage-reranking officialmentioned in papermentioned on GitHubpytorchSyntology: 10 samples, 8 ran (3 instrument-failed) · 2 unverified report

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.

Code Syntology ran Syntology

14 samples harvested: 8 ran (of which 4 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 3 where Syntology's instrument failed) · 6 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

3ran · our draft was wrong
5ran
6unverified

Licence: 10 of the 14 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 2 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

DevSinghSachan/unsupervised-passage-reranking official repository 10 samples, 8 ran (3 instrument-failed) · 2 unverified
CustomDataLoader upr.py ran no licence file found · pointer only · d5901455e19a84f8 · report fixture: returned CustomDataLoader · level recorded 2026-09-22
DistributedBatchSampler upr.py ran no licence file found · pointer only · 4f65156d8be990b5 · report fixture: returned DistributedBatchSampler · level recorded 2026-09-22
OpenQADataset upr.py ran no licence file found · pointer only · a3c5fbbe7959f17b · report fixture: returned OpenQADataset · level recorded 2026-09-22
OpenRetrievalEvidenceDataset upr.py ran no licence file found · pointer only · ba8cd692f32803b2 · report fixture: returned OpenRetrievalEvidenceDataset · level recorded 2026-09-22
build_sample upr.py ran · our draft was wrong fingerprinted no licence file found · pointer only · 21e99db1be01d7eb · report fixture: signature row_id:int/0/int, context_ids:list/1/int · returned dict · level recorded 2026-09-22
get_one_epoch_dataloader upr.py ran no licence file found · pointer only · 61c86a4b8de629dd · report fixture: signature dataset:SimpleDataset/0/?, args:ArgsConfig/0/?, batch_size:NoneType/0/? · returned CustomDataLoader · level recorded 2026-09-22
get_open_retrieval_wiki_dataset upr.py ran · our draft was wrong no licence file found · pointer only · a1921ddd1ee47af6 · report fixture: signature args:Args/0/?, tokens_encode_func:callable/0/? · returned OpenRetrievalEvidenceDataset · level recorded 2026-09-22
get_openqa_dataset upr.py ran · our draft was wrong no licence file found · pointer only · c4f3e9bb67241b4c · report fixture: signature task_name:str/0/str, dataset_path:str/0/str, sample_rate:float/0/float · returned OpenQADataset · level recorded 2026-09-22
UnsupervisedPassageReranker upr.py unverified no licence file found · pointer only · 79f98dfffed2b010 · report
print_rank_0 upr.py unverified no licence file found · pointer only · 4d4b4d61d1dc8caa · report
castorini/pygaggle found in paper text by Syntology 4 samples, 0 ran · 4 unverified
Query pygaggle/rerank/transformer.py unverified Apache-2.0 (permissive) · fa40f72ce9f3d097 · report
QuestionAnsweringTransformerReranker pygaggle/rerank/transformer.py unverified Apache-2.0 (permissive) · d5d41b07008bdae5 · report
Reranker pygaggle/rerank/transformer.py unverified Apache-2.0 (permissive) · cbf50e14db93384e · report
Text pygaggle/rerank/transformer.py unverified Apache-2.0 (permissive) · 31c7b4b7bfee3a66 · report

Method as code Syntology

What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it. Siblings are assemblies lifted from this paper in the same batch for the same method: alternative readings kept side by side; none replaces or supersedes another.

2 assemblies on this paper: 2 harvested, 0 generated, listed in 1 groups (siblings lifted in one batch form one group).

2 sibling assemblies for zero-shot question generation model-based re-ranking method (harvested), lifted in the same batch on 2026-09-09: alternative readings kept side by side; none replaces or supersedes another.

harvested Assembly for zero-shot question generation model-based re-ranking method (graph method: zero-shot question generation model-based re-ranking method). 10 bricks; individually on a fixture: 8 ran (of which 4 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified. The assembly has not been run end-to-end.

one of 2 siblings

  1. UnsupervisedPassageReranker entry · level 0 · unverified · 79f98dfffed2b010
  2. get_one_epoch_dataloader helper · level 1 · ran · 61c86a4b8de629dd
  3. get_open_retrieval_wiki_dataset helper · level 1 · ran · our draft was wrong · a1921ddd1ee47af6
  4. get_openqa_dataset helper · level 1 · ran · our draft was wrong · c4f3e9bb67241b4c
  5. print_rank_0 helper · level 0 · unverified · 4d4b4d61d1dc8caa
  6. CustomDataLoader helper · level 1 · ran · d5901455e19a84f8
  7. DistributedBatchSampler helper · level 1 · ran · 4f65156d8be990b5
  8. OpenRetrievalEvidenceDataset helper · level 1 · ran · ba8cd692f32803b2
  9. OpenQADataset helper · level 1 · ran · a3c5fbbe7959f17b
  10. build_sample helper · level 1 · ran · our draft was wrong · 21e99db1be01d7eb

harvested Assembly for zero-shot question generation model-based re-ranking method (graph method: zero-shot question generation model-based re-ranking method). 4 bricks; individually on a fixture: 0 ran · 4 unverified. The assembly has not been run end-to-end.

one of 2 siblings

  1. QuestionAnsweringTransformerReranker entry · level 0 · unverified · d5d41b07008bdae5
  2. Query helper · level 0 · unverified · fa40f72ce9f3d097
  3. Reranker helper · level 0 · unverified · cbf50e14db93384e
  4. Text helper · level 0 · unverified · 31c7b4b7bfee3a66

Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="2204.07496") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Language ModelingLanguage ModellingOpen-Domain Question AnsweringOpen-Ended Question AnsweringPassage RetrievalQuestion AnsweringQuestion GenerationQuestion-GenerationRe-RankingRetrieval

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

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