Methods › Natural Language Processing › Autoregressive Transformers › Transformer-XL

Transformer-XL

64 papers tagged archive 2025-07-28

Introduced by Zihang Dai et al. in Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context

archive 2025-07-28 Description, source and code snippet are the archive's method entry.

Transformer-XL (meaning extra long) is a Transformer architecture that introduces the notion of recurrence to the deep self-attention network. Instead of computing the hidden states from scratch for each new segment, Transformer-XL reuses the hidden states obtained in previous segments. The reused hidden states serve as memory for the current segment, which builds up a recurrent connection between the segments. As a result, modeling very long-term dependency becomes possible because information can be propagated through the recurrent connections. As an additional contribution, the Transformer-XL uses a new relative positional encoding formulation that generalizes to attention lengths longer than the one observed during training.

PaperSource

In Syntology repository known, no verified implementation (declared_code; repositories: 5 listed of 36 in the graph, strongest link: official). This answer is about arXiv:1901.02860, the paper the archive credits with this method.

Code Syntology holds under other names, as the lookup lists them (code_nearby); not a complete list, and none of them is this method.

Origin paper of this answer, arXiv:1901.02860 (its page on this site · its page on Syntology): Syntology's run record for its harvested code, 67 ran (of which 37 constructed an object rather than computing a result; 49 with no instrument failure: 4 honoured, 1 violated, 44 with no contract checked; 18 where Syntology's instrument failed) · 76 unverified (of 143 harvested samples) · 43 pointer-only (licence). The instrument figure counts failures of Syntology's instrument, not of the code. Ran means executed on a synthesized input, not that the code is correct.

Syntology's have check for this name (free, it answers coverage only), read 2026-10-05; ask it again live. A level is the served verification level of that one answer; nothing here is summed across methods.

What each level means, quoted from Syntology's server card: V0 “imports”; V1 “executes against a synthesized fixture and returns a value of the recorded type”; 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.” The card adds: “No rung on this ladder compares the served code against the authors' implementation, so treat every level as evidence about runnability and internal agreement, not about matching the paper's results.” A level quoted in two parts is one definition the card writes as two clauses joined by a double hyphen, each clause quoted on its own (how these levels are quoted).

Papers archive 2025-07-28

archive papers tagged: 64 · with a code link: 34 · where Syntology ran a sample: 14 (13 with a run with no instrument failure, 1 where every run was a failure of Syntology's instrument) Syntology

Show: all tagged papersonly where code ran (14 of 64 tagged: 13 with a run with no instrument failure, 1 where every run was a failure of Syntology's instrument)

Page 1 of 1: papers 1 to 64 of 64, newest first by the archive's date (ties by slug), in archive order.

Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code, as “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the instrument figure counts failures of Syntology's instrument, not of the code. It is per sample and not a correctness claim. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from.

Tasks archive 2025-07-28

20 shown of 86 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.

TaskPapers
Language Modelling38
Language Modeling27
Decoder7
Machine Translation6
Speech Recognition5
Translation5
speech-recognition5
Text Generation4
Automatic Speech Recognition3
Automatic Speech Recognition (ASR)3
Paraphrase Identification3
Reinforcement Learning (RL)3
Sentence3
Word Embeddings3
Abstractive Text Summarization2
Deep Attention2
Deep Reinforcement Learning2
GPU2
Graph Neural Network2
Music Generation2

Usage over time archive 2025-07-28

Papers per year tagged with Transformer-XL: 2019 to 2025, peak 16 16 0 2019: 13 papers 2019 2020: 16 papers 2020 2021: 14 papers 2021 2022: 6 papers 2022 2023: 10 papers 2023 2024: 4 papers 2024 2025: 1 paper 2025
Papers per year the archive tags with this method, by the paper's archive date (64 dated). Bars are counts, not a trend claim.

Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).

Categories archive 2025-07-28

Autoregressive TransformersTransformers

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