Papers › Autoregressive Entity Retrieval

Autoregressive Entity Retrieval

2 Oct 2020ICLR 2021 1arXiv:2010.00904archive 2025-07-28

Nicola De Cao, Gautier Izacard, Sebastian Riedel, Fabio Petroni

Entities are at the center of how we represent and aggregate knowledge. For instance, Encyclopedias such as Wikipedia are structured by entities (e.g., one per Wikipedia article). The ability to retrieve such entities given a query is fundamental for knowledge-intensive tasks such as entity linking and open-domain question answering. Current approaches can be understood as classifiers among atomic labels, one for each entity. Their weight vectors are dense entity representations produced by encoding entity meta information such as their descriptions. This approach has several shortcomings: (i) context and entity affinity is mainly captured through a vector dot product, potentially missing fine-grained interactions; (ii) a large memory footprint is needed to store dense representations when considering large entity sets; (iii) an appropriately hard set of negative data has to be subsampled at training time. In this work, we propose GENRE, the first system that retrieves entities by generating their unique names, left to right, token-by-token in an autoregressive fashion. This mitigates the aforementioned technical issues since: (i) the autoregressive formulation directly captures relations between context and entity name, effectively cross encoding both; (ii) the memory footprint is greatly reduced because the parameters of our encoder-decoder architecture scale with vocabulary size, not entity count; (iii) the softmax loss is computed without subsampling negative data. We experiment with more than 20 datasets on entity disambiguation, end-to-end entity linking and document retrieval tasks, achieving new state-of-the-art or very competitive results while using a tiny fraction of the memory footprint of competing systems. Finally, we demonstrate that new entities can be added by simply specifying their names. Code and pre-trained models at https://github.com/facebookresearch/GENRE.

PaperPDFConference PDFCodeMethod as code

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.

Syntology holds a reference implementation of GENRE, generated from the paper text (not the authors' code), at level 3 on Syntology's ladder: V2 “two implementations GENERATED from the paper's signature and spec agree numerically (1e-6) on fixture inputs” “neither of the two ever read the authors' own code, so V2 measures how unambiguously the paper specifies the method, not fidelity to the authors' implementation (measured 2026-09-11, commit 75eaa77: cross_checked_by is a second LLM on 2,628 of 2,831 served samples)”; V3 “paper-derived property tests pass on both of those same two generations.” (quoted from Syntology's server card). For this implementation, level 3 is recorded, but its report lists no property test that passed on both. No rung compares this code against the authors' implementation. For agents: get_reference_implementation(name='GENRE') (how to connect); the free check have('2010.00904') needs no token.

For agents, on Syntology's MCP service (how to connect):

Code

facebookresearch/GENRE officialmentioned in papermentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation,... (arXiv:1910.13461; that paper's own run record: 40 ran (of which 7 constructed an object rather than computing a result; 30 with no instrument failure: 1 honoured, 2 violated, 27 with no contract checked; 10 where Syntology's instrument failed) · 13 unverified); nothing checks that they implement this paper's method. report
amzn/seqzero mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to SeqZero: Few-shot Compositional Semantic Parsing with Sequential Prompts and Zero-shot Models (arXiv:2205.07381; that paper's own run record: 2 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; 1 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. 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

Not run by Syntology. Nothing on this page verifies that the listed code works.

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. For a generated assembly, an independent peer is a second implementation generated separately from the same paper text; neither implementation read the authors' code. At level 2 the two agreed numerically on the fixture's inputs; level 3 is recorded when property tests derived from the paper also passed on both, and each level 3 card prints how many its report lists. A generated assembly's label was set when its code was generated for the method, and no model judged it; its card prints it as "by construction" or "not judged by a model". Where an assembly's phrase has no constructed figure, a brick that ran is not among the harvested samples this build reads, and whether a brick's run only constructed an object is read from that brick's harvested sample, so the figure was not counted; it does not say there were none.

1 assembly on this paper: 0 harvested, 1 generated.

generated Assembly for GENRE (graph method: GENRE), generated from the paper text, not the repository's code. 1 brick; individually on a fixture: 1 ran (1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified. Ran end-to-end against an independent peer; level 3 is recorded, but its report lists no property test that passed on both.

label matches by construction: the code was generated for this method (not judged by a model)

  1. compute_entity_linking_micro_f1 entry · level 3 · ran · honoured contract · 43da960e970e7a145e3483528b4cf6864a7ab8d112540db39c6d7e8c467b7687

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="2010.00904") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Entity DisambiguationEntity LinkingEntity RetrievalOpen-Domain Question AnsweringQuestion AnsweringRetrieval

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Entity Disambiguation ACE2004 GENRE Micro-F1 90.1 #5 of 6 Archive leaderboard report
Entity Disambiguation AIDA-CoNLL GENRE In-KB Accuracy 93.3 #10 of 20 Archive leaderboard report
Entity Disambiguation AQUAINT GENRE Micro-F1 89.9 #4 of 6 Archive leaderboard report
Entity Disambiguation MSNBC GENRE Micro-F1 94.3 #4 of 6 Archive leaderboard report
Entity Disambiguation WNED-CWEB GENRE Micro-F1 77.3 #5 of 7 Archive leaderboard report
Entity Disambiguation WNED-WIKI GENRE Micro-F1 87.4 #4 of 7 Archive leaderboard report
Entity Linking AIDA-CoNLL De Cao et al. (2021a) Micro-F1 strong 83.7 #9 of 17 Archive leaderboard report
Entity Linking Derczynski De Cao et al. (2021a) Micro-F1 54.1 #3 of 7 Archive leaderboard report
Entity Linking KILT: AIDA-YAGO2 GENRE Accuracy 89.85 #1 of 11 Archive leaderboard report
Entity Linking KILT: AIDA-YAGO2 GENRE KILT-AC 89.85 #1 of 11 Archive leaderboard report
Entity Linking KILT: AIDA-YAGO2 GENRE R-Prec 89.85 #1 of 11 Archive leaderboard report
Entity Linking KILT: AIDA-YAGO2 GENRE Recall@5 94.76 #1 of 11 Archive leaderboard report
Entity Linking KILT: WNED-CWEB GENRE Accuracy 71.22 #1 of 10 Archive leaderboard report
Entity Linking KILT: WNED-CWEB GENRE KILT-AC 71.22 #1 of 10 Archive leaderboard report
Entity Linking KILT: WNED-CWEB GENRE R-Prec 71.22 #1 of 10 Archive leaderboard report
Entity Linking KILT: WNED-CWEB GENRE Recall@5 79.22 #1 of 10 Archive leaderboard report
Entity Linking KILT: WNED-WIKI GENRE Accuracy 87.44 #1 of 10 Archive leaderboard report
Entity Linking KILT: WNED-WIKI GENRE KILT-AC 87.44 #1 of 10 Archive leaderboard report
Entity Linking KILT: WNED-WIKI GENRE R-Prec 87.44 #1 of 10 Archive leaderboard report
Entity Linking KILT: WNED-WIKI GENRE Recall@5 94.91 #1 of 10 Archive leaderboard report
Entity Linking MSNBC De Cao et al. (2021a) Micro-F1 73.7 #3 of 8 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

Softmax

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