Papers › KILT: a Benchmark for Knowledge Intensive Language Tasks

KILT: a Benchmark for Knowledge Intensive Language Tasks

4 Sep 2020NAACL 2021 4arXiv:2009.02252archive 2025-07-28

Fabio Petroni, Aleksandra Piktus, Angela Fan, Patrick Lewis, Majid Yazdani, Nicola De Cao, James Thorne, Yacine Jernite, Vladimir Karpukhin, Jean Maillard, Vassilis Plachouras, Tim Rocktäschel, Sebastian Riedel

Challenging problems such as open-domain question answering, fact checking, slot filling and entity linking require access to large, external knowledge sources. While some models do well on individual tasks, developing general models is difficult as each task might require computationally expensive indexing of custom knowledge sources, in addition to dedicated infrastructure. To catalyze research on models that condition on specific information in large textual resources, we present a benchmark for knowledge-intensive language tasks (KILT). All tasks in KILT are grounded in the same snapshot of Wikipedia, reducing engineering turnaround through the re-use of components, as well as accelerating research into task-agnostic memory architectures. We test both task-specific and general baselines, evaluating downstream performance in addition to the ability of the models to provide provenance. We find that a shared dense vector index coupled with a seq2seq model is a strong baseline, outperforming more tailor-made approaches for fact checking, open-domain question answering and dialogue, and yielding competitive results on entity linking and slot filling, by generating disambiguated text. KILT data and code are available at https://github.com/facebookresearch/KILT.

PaperPDFConference PDFCodeCode 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

No sample from the archive's official repository (facebookresearch/KILT) is linked to this paper; the 1 sample below comes from 1 community repository. Syntology harvested code from facebookresearch/KILT for another paper.

facebookresearch/KILT: Syntology's graph links these samples to Generating Information-Seeking Conversations from Unlabeled Documents (arXiv:2205.12609; that paper's own run record: 10 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified); nothing checks that they implement this paper's method.

Syntology 1 code sample harvested from 1 repository linked to this paper: 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: community (archive-listed): 1 sample from 1 repository, 1 ran (1 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.

No sample is linked to this paper from 2 of its repositories that Syntology harvested for other papers:

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

facebookresearch/KILT officialmentioned in papermentioned on GitHubMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Generating Information-Seeking Conversations from Unlabeled Documents (arXiv:2205.12609; that paper's own run record: 10 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified); nothing checks that they implement this paper's method. report
facebookresearch/editeval mentioned on GitHubCC0-1.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to AAAI id aaai_29863 (that paper's own run record: 14 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method. report
zouharvi/kb-shrink mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 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.

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

1 sample harvested: 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 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.

1ran · honoured contract

Licence: 1 of the 1 sample is 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 zouharvi/kb-shrink. “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.

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.

zouharvi/kb-shrink community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
get_train_data in 6 papers src/reduce_dim/autoencoder/model.py ran · honoured contract no licence file found · pointer only · d5d38123e280f4e0 · report fixture: signature data:dict/0/?, train_key:str/0/str, train_crop_n:int/0/int · returned ndarray · level recorded 2026-09-22

Tasks

Entity LinkingFact CheckingFact VerificationOpen-Domain DialogOpen-Domain Question AnsweringQuestion AnsweringSlot Filling

Datasets

Introduced by this paper, per the archive.

KILT

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Entity Linking KILT: AIDA-YAGO2 T5-base Accuracy 74.05 #5 of 11 Archive leaderboard report
Entity Linking KILT: AIDA-YAGO2 T5-base KILT-AC 74.05 #5 of 11 Archive leaderboard report
Entity Linking KILT: AIDA-YAGO2 T5-base R-Prec 74.05 #5 of 11 Archive leaderboard report
Entity Linking KILT: AIDA-YAGO2 T5-base Recall@5 74.05 #5 of 11 Archive leaderboard report
Entity Linking KILT: WNED-CWEB T5-base Accuracy 49.29 #3 of 10 Archive leaderboard report
Entity Linking KILT: WNED-CWEB T5-base KILT-AC 49.29 #3 of 10 Archive leaderboard report
Entity Linking KILT: WNED-CWEB T5-base R-Prec 49.29 #3 of 10 Archive leaderboard report
Entity Linking KILT: WNED-CWEB T5-base Recall@5 49.29 #3 of 10 Archive leaderboard report
Entity Linking KILT: WNED-WIKI T5-base Accuracy 47.13 #4 of 10 Archive leaderboard report
Entity Linking KILT: WNED-WIKI T5-base KILT-AC 47.13 #4 of 10 Archive leaderboard report
Entity Linking KILT: WNED-WIKI T5-base R-Prec 47.13 #4 of 10 Archive leaderboard report
Entity Linking KILT: WNED-WIKI T5-base Recall@5 47.13 #4 of 10 Archive leaderboard report
Fact Verification KILT: FEVER RAG Accuracy 86.31 #7 of 33 Archive leaderboard report
Fact Verification KILT: FEVER RAG KILT-AC 53.45 #7 of 33 Archive leaderboard report
Fact Verification KILT: FEVER RAG R-Prec 61.94 #7 of 33 Archive leaderboard report
Fact Verification KILT: FEVER RAG Recall@5 75.55 #7 of 33 Archive leaderboard report
Fact Verification KILT: FEVER T5-base Accuracy 76.3 #17 of 33 Archive leaderboard report
Fact Verification KILT: FEVER T5-base KILT-AC 0.0 #17 of 33 Archive leaderboard report
Fact Verification KILT: FEVER T5-base R-Prec 0.0 #17 of 33 Archive leaderboard report
Fact Verification KILT: FEVER T5-base Recall@5 0.0 #17 of 33 Archive leaderboard report
Open-Domain Dialog KILT: Wizard of Wikipedia T5-base F1 13.53 #20 of 21 Archive leaderboard report
Open-Domain Dialog KILT: Wizard of Wikipedia T5-base KILT-F1 0.0 #20 of 21 Archive leaderboard report
Open-Domain Dialog KILT: Wizard of Wikipedia T5-base KILT-RL 0.0 #20 of 21 Archive leaderboard report
Open-Domain Dialog KILT: Wizard of Wikipedia T5-base R-Prec 0.0 #20 of 21 Archive leaderboard report
Open-Domain Dialog KILT: Wizard of Wikipedia T5-base ROUGE-L 12.4 #20 of 21 Archive leaderboard report
Open-Domain Dialog KILT: Wizard of Wikipedia T5-base Recall@5 0.0 #20 of 21 Archive leaderboard report
Open-Domain Question Answering KILT: ELI5 T5-base F1 16.1 #11 of 16 Archive leaderboard report
Open-Domain Question Answering KILT: ELI5 T5-base KILT-F1 0.0 #11 of 16 Archive leaderboard report
Open-Domain Question Answering KILT: ELI5 T5-base KILT-RL 0.0 #11 of 16 Archive leaderboard report
Open-Domain Question Answering KILT: ELI5 T5-base R-Prec 0.0 #11 of 16 Archive leaderboard report
Open-Domain Question Answering KILT: ELI5 T5-base ROUGE-L 19.08 #11 of 16 Archive leaderboard report
Open-Domain Question Answering KILT: ELI5 T5-base Recall@5 0.0 #11 of 16 Archive leaderboard report
Open-Domain Question Answering KILT: HotpotQA T5-base EM 12.64 #13 of 14 Archive leaderboard report
Open-Domain Question Answering KILT: HotpotQA T5-base F1 19.57 #13 of 14 Archive leaderboard report
Open-Domain Question Answering KILT: HotpotQA T5-base KILT-EM 0.0 #13 of 14 Archive leaderboard report
Open-Domain Question Answering KILT: HotpotQA T5-base KILT-F1 0.0 #13 of 14 Archive leaderboard report
Open-Domain Question Answering KILT: HotpotQA T5-base R-Prec 0.0 #13 of 14 Archive leaderboard report
Open-Domain Question Answering KILT: HotpotQA T5-base Recall@5 0.0 #13 of 14 Archive leaderboard report
Open-Domain Question Answering KILT: Natural Questions T5-base EM 19.6 #15 of 16 Archive leaderboard report
Open-Domain Question Answering KILT: Natural Questions T5-base F1 27.73 #15 of 16 Archive leaderboard report
Open-Domain Question Answering KILT: Natural Questions T5-base KILT-EM 0.0 #15 of 16 Archive leaderboard report
Open-Domain Question Answering KILT: Natural Questions T5-base KILT-F1 0.0 #15 of 16 Archive leaderboard report
Open-Domain Question Answering KILT: Natural Questions T5-base R-Prec 0.0 #15 of 16 Archive leaderboard report
Open-Domain Question Answering KILT: Natural Questions T5-base Recall@5 0.0 #15 of 16 Archive leaderboard report
Open-Domain Question Answering KILT: TriviaQA T5-base EM 18.11 #15 of 15 Archive leaderboard report
Open-Domain Question Answering KILT: TriviaQA T5-base F1 27.83 #15 of 15 Archive leaderboard report
Open-Domain Question Answering KILT: TriviaQA T5-base KILT-EM 0.0 #15 of 15 Archive leaderboard report
Open-Domain Question Answering KILT: TriviaQA T5-base KILT-F1 0.0 #15 of 15 Archive leaderboard report
Open-Domain Question Answering KILT: TriviaQA T5-base R-Prec 0.0 #15 of 15 Archive leaderboard report
Open-Domain Question Answering KILT: TriviaQA T5-base Recall@5 0.0 #15 of 15 Archive leaderboard report
Question Answering KILT: ELI5 T5-base F1 16.1 #5 of 7 Archive leaderboard report
Question Answering KILT: ELI5 T5-base Rouge-L 19.08 #5 of 7 Archive leaderboard report
Question Answering KILT: ELI5 BART+DPR F1 17.88 #6 of 7 Archive leaderboard report
Question Answering KILT: ELI5 BART+DPR Rouge-L 17.41 #6 of 7 Archive leaderboard report
Question Answering KILT: ELI5 RAG F1 14.51 #7 of 7 Archive leaderboard report
Question Answering KILT: ELI5 RAG Rouge-L 14.05 #7 of 7 Archive leaderboard report
Slot Filling KILT: T-REx T5-base Accuracy 43.56 #18 of 20 Archive leaderboard report
Slot Filling KILT: T-REx T5-base F1 50.61 #18 of 20 Archive leaderboard report
Slot Filling KILT: T-REx T5-base KILT-AC 0.0 #18 of 20 Archive leaderboard report
Slot Filling KILT: T-REx T5-base KILT-F1 0.0 #18 of 20 Archive leaderboard report
Slot Filling KILT: T-REx T5-base R-Prec 0.0 #18 of 20 Archive leaderboard report
Slot Filling KILT: T-REx T5-base Recall@5 0.0 #18 of 20 Archive leaderboard report
Slot Filling KILT: Zero Shot RE T5-base Accuracy 9.02 #20 of 21 Archive leaderboard report
Slot Filling KILT: Zero Shot RE T5-base F1 13.52 #20 of 21 Archive leaderboard report
Slot Filling KILT: Zero Shot RE T5-base KILT-AC 0.0 #20 of 21 Archive leaderboard report
Slot Filling KILT: Zero Shot RE T5-base KILT-F1 0.0 #20 of 21 Archive leaderboard report
Slot Filling KILT: Zero Shot RE T5-base R-Prec 0.0 #20 of 21 Archive leaderboard report
Slot Filling KILT: Zero Shot RE T5-base Recall@5 0.0 #20 of 21 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.

Methods

LSTMSeq2SeqSigmoid ActivationTanh Activation

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