Papers › Abstractors and relational cross-attention: An inductive bias for explicit relational...

Abstractors and relational cross-attention: An inductive bias for explicit relational reasoning in Transformers

1 Apr 2023arXiv:2304.00195archive 2025-07-28

Awni Altabaa, Taylor Webb, Jonathan Cohen, John Lafferty

An extension of Transformers is proposed that enables explicit relational reasoning through a novel module called the Abstractor. At the core of the Abstractor is a variant of attention called relational cross-attention. The approach is motivated by an architectural inductive bias for relational learning that disentangles relational information from object-level features. This enables explicit relational reasoning, supporting abstraction and generalization from limited data. The Abstractor is first evaluated on simple discriminative relational tasks and compared to existing relational architectures. Next, the Abstractor is evaluated on purely relational sequence-to-sequence tasks, where dramatic improvements are seen in sample efficiency compared to standard Transformers. Finally, Abstractors are evaluated on a collection of tasks based on mathematical problem solving, where consistent improvements in performance and sample efficiency are observed.

PaperPDFCodeCode Syntology ran

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2304.00195")

Code

Syntology Ran 9 of 12 code samples harvested from 1 repository linked to this paper; 3 have no recorded run. Of those that ran: 1 ran · honoured contract; 3 ran · our draft was wrong; 5 ran with no contract checked.

By repository: official repository: 12 samples from 1 repository, 9 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

awni00/abstractor officialmentioned in papermentioned on GitHubtf 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.

Code Syntology ran Syntology

12 samples harvested; 9 ran; 1 honoured the contract we drafted; 3 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

1ran · honoured contract
3ran · our draft was wrong
5ran
3unverified

Licence: 12 of the 12 samples are 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 awni00/abstractor. “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. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (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 from a repository marked official are listed first. 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 four 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; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). 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.

AddPositionalEmbedding awni00/abstractor/abstracters.py official repository ran · metamorphic tier: deterministic GPL-3.0 (copyleft) · pointer only · 902fac1c90d0a3a9 · report
BaseAttention awni00/abstractor/abstracters.py official repository ran GPL-3.0 (copyleft) · pointer only · b6ee3cfab9e23fe6 · report
FeedForward awni00/abstractor/abstracters.py official repository ran GPL-3.0 (copyleft) · pointer only · afc5f405a2e74f64 · report
GlobalSelfAttention awni00/abstractor/abstracters.py official repository ran GPL-3.0 (copyleft) · pointer only · cd3c52764d10eb2a · report
MultiHeadAttention awni00/abstractor/abstracters.py official repository ran GPL-3.0 (copyleft) · pointer only · 2159f6374bdb0366 · report
_build_attention_equation awni00/abstractor/abstracters.py official repository ran · our draft was wrong GPL-3.0 (copyleft) · pointer only · ac594e861d76d88b · report
_build_proj_equation awni00/abstractor/abstracters.py official repository ran · our draft was wrong fingerprinted GPL-3.0 (copyleft) · pointer only · a19c79a5dd4448d8 · report
_get_output_shape awni00/abstractor/abstracters.py official repository ran · our draft was wrong fingerprinted GPL-3.0 (copyleft) · pointer only · 8dfc0cd5c0042e8f · report
create_positional_encoding awni00/abstractor/abstracters.py official repository ran · honoured contract fingerprinted GPL-3.0 (copyleft) · pointer only · e4da176e568a85ee · report
RelationalAbstracter awni00/abstractor/abstracters.py official repository unverified GPL-3.0 (copyleft) · pointer only · dc606b9fae039cdc · report
RelationalAbstracterLayer awni00/abstractor/abstracters.py official repository unverified GPL-3.0 (copyleft) · pointer only · bcb5267bdfd0bada · report
RelationalAttention awni00/abstractor/abstracters.py official repository unverified GPL-3.0 (copyleft) · pointer only · ab85963b77d97a76 · report

Tasks

Inductive BiasMathematical Problem-SolvingRelational Reasoning

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Absolute Position EncodingsAdamAttentionBPEDense ConnectionsDropoutLabel SmoothingLayer NormalizationLinear LayerMulti-Head AttentionPosition-Wise Feed-Forward LayerResidual ConnectionSoftmaxTransformer

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