Papers › Diverse Beam Search: Decoding Diverse Solutions from Neural Sequence Models

Diverse Beam Search: Decoding Diverse Solutions from Neural Sequence Models

7 Oct 2016arXiv:1610.02424archive 2025-07-28

Ashwin K. Vijayakumar, Michael Cogswell, Ramprasath R. Selvaraju, Qing Sun, Stefan Lee, David Crandall, Dhruv Batra

Neural sequence models are widely used to model time-series data. Equally ubiquitous is the usage of beam search (BS) as an approximate inference algorithm to decode output sequences from these models. BS explores the search space in a greedy left-right fashion retaining only the top-B candidates - resulting in sequences that differ only slightly from each other. Producing lists of nearly identical sequences is not only computationally wasteful but also typically fails to capture the inherent ambiguity of complex AI tasks. To overcome this problem, we propose Diverse Beam Search (DBS), an alternative to BS that decodes a list of diverse outputs by optimizing for a diversity-augmented objective. We observe that our method finds better top-1 solutions by controlling for the exploration and exploitation of the search space - implying that DBS is a better search algorithm. Moreover, these gains are achieved with minimal computational or memory over- head as compared to beam search. To demonstrate the broad applicability of our method, we present results on image captioning, machine translation and visual question generation using both standard quantitative metrics and qualitative human studies. Further, we study the role of diversity for image-grounded language generation tasks as the complexity of the image changes. We observe that our method consistently outperforms BS and previously proposed techniques for diverse decoding from neural sequence models.

PaperPDFCodeCode Syntology ran

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

The archive's official repository (ashwinkalyan/dbs) was not harvested; the 13 samples below come from 7 community repositories, and 1 more is identical to code Syntology harvested from another paper's repository.

Syntology 14 code samples: 13 from 7 repositories linked to this paper, 1 identical to code harvested from another paper's repository. Across all 14: 7 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 1 violated, 1 with no contract checked; 5 where Syntology's instrument failed) · 7 unverified. Where Syntology's instrument failed: 3 where our contract draft was wrong; 2 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 13 samples from 7 repositories, 6 ran (2 with no instrument failure; 4 where Syntology's instrument failed); 1 identical to code first harvested elsewhere. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

No sample is linked to this paper from 8 of its repositories that Syntology harvested for other papers:

Levels written on 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 1 of the 7 samples that ran has no recorded date.

25 repositories listed; official and paper-mentioned ones first.

ashwinkalyan/dbs officialmentioned in papertorchSyntology: not harvested report
StatNLP/ada4asr mentioned on GitHubpytorchMITSyntology: 2 samples, 1 ran (1 instrument-failed) · 1 unverified report
SunJiamei/LRP-imagecaptioning-pytorch mentioned on GitHubpytorchSyntology: not harvested report
ahmetustun/fairseq mentioned on GitHubpytorchMITSyntology: 3 samples, 1 ran (1 instrument-failed) · 2 unverified report
bzylich/persona-chatbot mentioned on GitHubpytorchSyntology: not harvested report
cindyxinyiwang/fairseq mentioned on GitHubpytorchMITSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
codecaution/evomoe mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to EvoMoE: An Evolutional Mixture-of-Experts Training Framework via Dense-To-Sparse Gate (arXiv:2112.14397; that paper's own run record: 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
dannigt/fairseq mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Learning an Artificial Language for Knowledge-Sharing in Multilingual Translation (arXiv:2211.01292; that paper's own run record: 2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified); nothing checks that they implement this paper's method. report
facebookresearch/fairseq mentioned on GitHubpytorchMITSyntology: not harvested report
fairseq/fairseq mentioned on GitHubpytorchMITSyntology: 3 samples, 2 ran (1 instrument-failed) · 1 unverified report
formiel/fairseq mentioned on GitHubpytorchMITSyntology: not harvested report
hlt-mt/fbk-fairseq mentioned on GitHubpytorchNOASSERTIONSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to How do Hyenas deal with Human Speech? Speech Recognition and Translation with ConfHyena (arXiv:2402.13208; that paper's own run record: 3 ran (of which 1 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
hltchkust/cantonese-asr mentioned on GitHubpytorchSyntology: not harvested report
jerinphilip/fairseq-ilmt mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to A Multilingual Parallel Corpora Collection Effort for Indian Languages (arXiv:2007.07691; that paper's own run record: 4 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 1 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 6 unverified); nothing checks that they implement this paper's method. report
jungokasai/t2r mentioned on GitHubpytorchMITSyntology: 1 sample, 1 ran (1 instrument-failed) · 0 unverified report
libeineu/GPKD mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Learning Light-Weight Translation Models from Deep Transformer (arXiv:2012.13866; that paper's own run record: 2 ran (of which 2 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified; every one of the 2 samples that ran constructed an object rather than computing a result); nothing checks that they implement this paper's method. report
libeineu/SDT-Training mentioned on GitHubpytorchNOASSERTIONSyntology: not harvested report
lucylow/En_francais_si_vous_plait- mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to fairseq: A Fast, Extensible Toolkit for Sequence Modeling (arXiv:1904.01038; that paper's own run record: 3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 8 unverified); nothing checks that they implement this paper's method. report
marccanby/bidi_decoding mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Unsupervised Speech Recognition (arXiv:2105.11084; that paper's own run record: 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
mgaido91/FBK-fairseq-ST mentioned on GitHubpytorchSyntology: not harvested report
raymondhs/fairseq-extensible-mbart mentioned on GitHubpytorchMITSyntology: 1 sample, 0 ran · 1 unverified report
sarapapi/fbk-fairseq mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Speechformer: Reducing Information Loss in Direct Speech Translation (arXiv:2109.04574; that paper's own run record: 2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified); nothing checks that they implement this paper's method. report
stevezheng23/fairseq_extension mentioned on GitHubpytorchMITSyntology: 2 samples, 0 ran · 2 unverified report
utanaka2000/fairseq mentioned on GitHubpytorchMITSyntology: not harvested report
windweller/PragmaticVQA mentioned on GitHubSyntology: not harvested 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.

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

14 samples harvested: 7 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 1 violated, 1 with no contract checked; 5 where Syntology's instrument failed) · 7 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

1ran · violated contract
3ran · our draft was wrong
2ran; the contract check could not run
1ran
7unverified

Licence: 14 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 7 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. 1 sample is listed last, in a group without a repository. “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”. For 1 sample that ran, the graph records a signature this page does not show: an argument's recorded type or element kind is a printout of an object in Syntology's harness (such as a mock object, a class or a pandas printout), not the type of an input, so it does not describe the call's shape. “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.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity.

StatNLP/ada4asr community (archive-listed) 2 samples, 1 ran (1 instrument-failed) · 1 unverified
safe_readline in 67 papers fairseq/binarizer.py ran · our draft was wrong MIT recorded; this copy not marked cleared · pointer only · 82bdf940665aeeb4 · report fixture: signature f:StringIO/0/? · returned str · level recorded 2026-09-24
all_reduce in 42 papers fairseq/distributed_utils.py unverified MIT recorded; this copy not marked cleared · pointer only · 199e96db5edd0edd · report
ahmetustun/fairseq community (archive-listed) 3 samples, 1 ran (1 instrument-failed) · 2 unverified
url_to_filename in 73 papers fairseq/file_utils.py ran · our draft was wrong fingerprinted MIT recorded; this copy not marked cleared · pointer only · 9418b43048e4e4ec · report fixture: signature url:str/0/str, etag:str/0/str · returned str · level recorded 2026-09-24
filename_to_url in 54 papers fairseq/file_utils.py unverified MIT recorded; this copy not marked cleared · pointer only · aafdc12f01ab388f · report
load_archive_file in 14 papers fairseq/file_utils.py unverified MIT recorded; this copy not marked cleared · pointer only · 5603a04b6103554e · report
cindyxinyiwang/fairseq community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
find_offsets in 7 papers fairseq/file_chunker_utils.py ran MIT recorded; this copy not marked cleared · pointer only · 840d9070e4fd8ba6 · report fixture: signature filename:str/0/str, num_chunks:int/0/int · returned list · level recorded 2026-09-24
fairseq/fairseq community (archive-listed) 3 samples, 2 ran (1 instrument-failed) · 1 unverified
distributed_init in 19 papers fairseq/distributed_utils.py ran; the contract check could not run (DEP_MISSING) MIT recorded; this copy not marked cleared · pointer only · 2e69129bbcf930e7 · report fixture: returned int · level recorded 2026-09-24
is_master in 43 papers fairseq/distributed_utils.py ran · violated contract MIT recorded; this copy not marked cleared · pointer only · 90b79fe15491de83 · report fixture: signature args:Args/0/? · returned bool · level recorded 2026-09-24
load_archive_file in 14 papers fairseq/file_utils.py unverified MIT recorded; this copy not marked cleared · pointer only · bf870e076be41d5d · report
jungokasai/t2r community (archive-listed) 1 sample, 1 ran (1 instrument-failed) · 0 unverified
distributed_init in 19 papers fairseq/distributed_utils.py ran; the contract check could not run (DEP_MISSING) MIT recorded; this copy not marked cleared · pointer only · 07969f7041022050 · report fixture: signature args:Args/0/? · returned int · level recorded 2026-09-24
raymondhs/fairseq-extensible-mbart community (archive-listed) 1 sample, 0 ran · 1 unverified
load_archive_file in 14 papers fairseq/file_utils.py unverified MIT recorded; this copy not marked cleared · pointer only · 0d372aa1e290a613 · report
stevezheng23/fairseq_extension community (archive-listed) 2 samples, 0 ran · 2 unverified
filename_to_url in 54 papers fairseq/file_utils.py unverified MIT recorded; this copy not marked cleared · pointer only · b1a033619f614e17 · report
load_archive_file in 14 papers fairseq/file_utils.py unverified MIT recorded; this copy not marked cleared · pointer only · bd3fe80662b28bc7 · report
Repository not located 1 sample, 1 ran (1 instrument-failed) · 0 unverified
1 sample is identical to code Syntology harvested from another paper's repository; this paper's own copy was not located, so no repository is named and no licence is recorded.
label_smoothed_nll_loss in 43 papers repository not located ran · our draft was wrong licence of this copy not recorded · 26da4f92ba56e785 · report fixture: signature lprobs:Tensor/2/float, target:Tensor/1/int, epsilon:float/0/float, ignore_index:NoneType/0/?, reduce:bool/0/bool · returned tuple · level recorded, date not recorded

Tasks

DiversityImage CaptioningMachine TranslationQuestion GenerationQuestion-GenerationText GenerationTime Series Analysis

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