Papers › Abstraction Alignment: Comparing Model-Learned and Human-Encoded Conceptual Relationships

Abstraction Alignment: Comparing Model-Learned and Human-Encoded Conceptual Relationships

17 Jul 2024arXiv:2407.12543archive 2025-07-28

Angie Boggust, Hyemin Bang, Hendrik Strobelt, Arvind Satyanarayan

While interpretability methods identify a model's learned concepts, they overlook the relationships between concepts that make up its abstractions and inform its ability to generalize to new data. To assess whether models' have learned human-aligned abstractions, we introduce abstraction alignment, a methodology to compare model behavior against formal human knowledge. Abstraction alignment externalizes domain-specific human knowledge as an abstraction graph, a set of pertinent concepts spanning levels of abstraction. Using the abstraction graph as a ground truth, abstraction alignment measures the alignment of a model's behavior by determining how much of its uncertainty is accounted for by the human abstractions. By aggregating abstraction alignment across entire datasets, users can test alignment hypotheses, such as which human concepts the model has learned and where misalignments recur. In evaluations with experts, abstraction alignment differentiates seemingly similar errors, improves the verbosity of existing model-quality metrics, and uncovers improvements to current human abstractions.

PaperPDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also 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.

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

Code

Syntology 16 code samples harvested from 1 repository linked to this paper: 12 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 6 where Syntology's instrument failed) · 4 unverified. Where Syntology's instrument failed: 6 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 16 samples from 1 repository, 12 ran (6 with no instrument failure; 6 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written on 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

mitvis/abstraction-alignment officialmentioned in paperpytorchSyntology: 16 samples, 12 ran (6 instrument-failed) · 4 unverified 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

16 samples harvested: 12 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 6 where Syntology's instrument failed) · 4 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

6ran · our draft was wrong
6ran
4unverified

Licence: 16 of the 16 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 mitvis/abstraction-alignment. “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. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (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 are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. 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 six 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; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. 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.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity.

mitvis/abstraction-alignment official repository 16 samples, 12 ran (6 instrument-failed) · 4 unverified
abstraction_match metrics.py ran no licence file found · pointer only · c0e5eaaf5e982fdf · report fixture: signature fitted_abstractions:list/1/FittedAbstraction, level:int/0/int, next_level:int/0/int · returned float64 · level recorded 2026-09-24
cifar_train_transform util/cifar/cifar_util.py ran · our draft was wrong no licence file found · pointer only · afad9ee0a982459e · report fixture: signature data_augmentation:bool/0/bool · returned Compose · level recorded 2026-09-24
concept_coconfusion metrics.py ran no licence file found · pointer only · 80390fd2467092e9 · report fixture: signature fitted_abstractions:list/1/dict, threshold:float/0/float, normalization:NoneType/0/? · returned dict · level recorded 2026-09-24
load_task_data extract_data_llm.py ran no licence file found · pointer only · 098f27925e98742c · report fixture: signature task_id:str/0/str, data_dir:str/0/str · returned dict · level recorded 2026-09-24
parse_code in 7 papers abstraction_graph_mimic.py ran · our draft was wrong fingerprinted no licence file found · pointer only · 0b12ee4545def1a9 · report fixture: signature code:str/0/str · returned tuple · level recorded 2026-09-24
propagate in 7 papers abstraction_graph_toy_example.py ran no licence file found · pointer only · 125298654275b542 · report fixture: signature outputs:list/1/ndarray, abstraction_graph:AbstractionGraph/0/? · returned AbstractionGraph · level recorded 2026-09-24
resnet20 in 42 papers util/cifar/resnet.py ran · our draft was wrong no licence file found · pointer only · a10d10e7bcf4cb4a · report fixture: signature num_classes:int/0/int · returned ResNet · level recorded 2026-09-24
resnet32 in 47 papers util/cifar/resnet.py ran · our draft was wrong no licence file found · pointer only · 85364deb653f2cf6 · report fixture: signature num_classes:int/0/int · returned ResNet · level recorded 2026-09-24
resnet44 in 19 papers util/cifar/resnet.py ran · our draft was wrong no licence file found · pointer only · cd8b7f0a3a1b23f4 · report fixture: signature num_classes:int/0/int · returned ResNet · level recorded 2026-09-24
serialize_abstraction_graph abstraction_graph_cifar.py ran · our draft was wrong no licence file found · pointer only · a50fb6bdeb2ed09f · report fixture: signature abstraction_graph:AbstractionGraph/0/? · returned list · level recorded 2026-09-24
show_abstraction_graph abstraction_graph_cifar.py ran no licence file found · pointer only · cbb89f885c84850b · report fixture: signature abstraction_graph:MockAbstractionGraph/0/?, hide_zeros:bool/0/bool · returned str · level recorded 2026-09-24
test in 377 papers util/cifar/cifar_train.py ran no licence file found · pointer only · 2137246c139ab515 · report fixture: signature model:callable/0/?, test_loader:list/1/tuple · returned float · level recorded 2026-09-24
concept_coconfusion_inplace metrics.py unverified no licence file found · pointer only · e3429d740fac38e0 · report
get_synset_name extract_data_llm.py unverified no licence file found · pointer only · 1e9a24fd66a07ed6 · report
get_synsets_relatives extract_data_llm.py unverified no licence file found · pointer only · 69cba738f38ced16 · report
load_dataset in 276 papers util/cifar/cifar_util.py unverified no licence file found · pointer only · 03dd5e33de52b3cf · report

Tasks

Benchmarking

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

SET

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