Methods › General › Attention Modules › Talking-Heads Attention
Talking-Heads Attention
Introduced by Noam Shazeer et al. in Talking-Heads Attention
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
Talking-Heads Attention is a variation on multi-head attention which includes linear projections across the attention-heads dimension, immediately before and after the softmax operation. In multi-head attention, the different attention heads perform separate computations, which are then summed at the end. Talking-Heads Attention breaks that separation. Two additional learned linear projections are inserted, Pₗ and P_w, which transform the attention-logits and the attention weights respectively, moving information across attention heads. Instead of one "heads" dimension h across the whole computation, we now have three separate heads dimensions: hₖ, h, and hᵥ, which can optionally differ in size (number of "heads"). hₖ refers to the number of attention heads for the keys and the queries. h refers to the number of attention heads for the logits and the weights, and hᵥ refers to the number of attention heads for the values.
In Syntology harvested code stored, below machine verification (unverified_code; harvested), served level V1; retrieve with get_harvested_code_for_paper(arxiv_id='2003.02436'). Repositories: 4 listed of 4 in the graph, strongest link: official. The lookup matched a paper by its title, arXiv:2003.02436, not a method entry. This answer is about arXiv:2003.02436, the paper the archive credits with this method.
Origin paper of this answer, arXiv:2003.02436 (its page on this site · its page on Syntology): Syntology's run record for its harvested code, 3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 2 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified (of 3 harvested samples) · 2 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: 1 · with a code link: 1 · where Syntology ran a sample: 1 (1 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 (1 of 1 tagged: 1 with a run with no instrument failure, 0 where every run was a failure of Syntology's instrument)
Page 1 of 1: paper 1 of 1, 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.
-
Talking-Heads Attention 5 Mar 2020 · 4 repositories · arXiv:2003.02436Syntology official: no sample here; runs from other or unrecorded repositories · 3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 2 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified (of 3 harvested samples) · 2 pointer-only (licence)
Tasks archive 2025-07-28
5 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.
| Task | Papers |
|---|---|
| Language Modeling | 1 |
| Language Modelling | 1 |
| Masked Language Modeling | 1 |
| Question Answering | 1 |
| Transfer Learning | 1 |
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