Methods › Natural Language Processing › Static Word Embeddings › Mirror-BERT
Mirror-BERT
Introduced by Fangyu Liu et al. in Fast, Effective, and Self-Supervised: Transforming Masked Language Models into Universal Lexical and Sentence Encoders
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
Mirror-BERT converts pretrained language models into effective universal text encoders without any supervision, in 20-30 seconds. It is an extremely simple, fast, and effective contrastive learning technique. It relies on fully identical or slightly modified string pairs as positive (i.e., synonymous) fine-tuning examples, and aims to maximise their similarity during identity fine-tuning.
In Syntology repository known, no verified implementation (declared_code; repositories: 1 listed of 1 in the graph, strongest link: official). This answer is about arXiv:2104.08027, 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.
- Policy Mirror Ascent · shares_name_tokens (shares name tokens with this name; a different method) · level V3 · retrieve with
get_reference_implementation(name='Policy Mirror Ascent') - stochastic mirror descent framework · shares_name_tokens (shares name tokens with this name; a different method) · level V3 · retrieve with
get_reference_implementation(name='stochastic mirror descent framework') - Adaptively Perturbed Mirror Descent (APMD) · shares_name_tokens (shares name tokens with this name; a different method) · level V3 · retrieve with
get_reference_implementation(name='Adaptively Perturbed Mirror Descent (APMD)') - one-pass algorithm based on the online mirror descent framework · shares_name_tokens (shares name tokens with this name; a different method) · level V2 · retrieve with
get_reference_implementation(name='one-pass algorithm based on the online mirror descent framework') - Robust Imitation via Mirror Descent Inverse Reinforcement Learning · shares_name_tokens (shares name tokens with this name; a different method) · level V2 · retrieve with
get_reference_implementation(name='Robust Imitation via Mirror Descent Inverse Reinforcement Learning')
Origin paper of this answer, arXiv:2104.08027 (its page on this site · its page on Syntology): Syntology's run record for its harvested code, 0 ran · 1 unverified (of 1 harvested sample). 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: 6 · with a code link: 6 · where Syntology ran a sample: 0 (0 with a run with no instrument failure, 0 where every run was a failure of Syntology's instrument) Syntology
Show: all tagged papersonly where code ran: none of the 6 tagged papers has a Syntology run on record
Page 1 of 1: papers 1 to 6 of 6, 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.
-
TaCL: Improving BERT Pre-training with Token-aware Contrastive Learning 7 Nov 2021 · 2 repositories · arXiv:2111.04198
-
Prix-LM: Pretraining for Multilingual Knowledge Base Construction 16 Oct 2021 · 1 repository · arXiv:2110.08443
-
Rewire-then-Probe: A Contrastive Recipe for Probing Biomedical Knowledge of Pre-trained Language Models 15 Oct 2021 · 1 repository · arXiv:2110.08173
-
Trans-Encoder: Unsupervised sentence-pair modelling through self- and mutual-distillations 27 Sep 2021 · 1 repository · arXiv:2109.13059
-
MirrorWiC: On Eliciting Word-in-Context Representations from Pretrained Language Models 19 Sep 2021 · 1 repository · arXiv:2109.09237
-
Fast, Effective, and Self-Supervised: Transforming Masked Language Models into Universal Lexical and Sentence Encoders 16 Apr 2021 · 1 repository · arXiv:2104.08027Syntology official: harvested, nothing ran · 0 ran · 1 unverified (of 1 harvested sample)
Tasks archive 2025-07-28
20 shown of 22 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.
Usage over time archive 2025-07-28
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
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