SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2408.01432 · NeurIPS · 2024

VLG-CBM: Training Concept Bottleneck Models with Vision-Language Guidance

U San, Tsui-Wei Weng, Divyansh Srivastava, Ge Yan

arXiv · PDF · Open in the Atlas

Code that ran

15 of 19 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 1 honoured the contract we drafted, 0 violated it and 1 has no contract verdict; 13 failures of our instrument; 4 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2408.01432.json · badge: /api/ran/2408.01432.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
Trustworthy-ML-Lab/Label-free-CBM canonical (classifier label)
classifier basis: census
15 ran · 4 no recorded run
FunctionStatusWhere it lives
add_index_to_dataloader Ran
ran; our contract draft was wrong, not the code
Trustworthy-ML-Lab/Label-free-CBM/glm_saga/elasticnet.py
pointer only (licence: NONE); the stored copy get_code serves, from importAmir/CI-CBM, is pointer only (licence: NONE) · get_code("7798dffe63b4a970")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Trustworthy-ML-Lab/Label-free-CBM when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

basic_clean Ran
ran; our contract draft was wrong, not the code
Trustworthy-ML-Lab/Label-free-CBM/clip/simple_tokenizer.py
pointer only (licence: NONE); the stored copy get_code serves, from ltpwy/MSCI, is pointer only (licence: NONE) · get_code("98f385d847636a3e")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Trustworthy-ML-Lab/Label-free-CBM when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

cos_similarity Ran
ran; our contract draft was wrong, not the code
Trustworthy-ML-Lab/Label-free-CBM/similarity.py
pointer only (licence: NONE); the stored copy get_code serves, from teresa-sc/concepts_in_vits, is pointer only (licence: NONE) · get_code("cc642412d4347cce")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Trustworthy-ML-Lab/Label-free-CBM when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

cos_similarity_cubed Ran
ran; our contract draft was wrong, not the code
Trustworthy-ML-Lab/Label-free-CBM/similarity.py
pointer only (licence: NONE); the stored copy get_code serves, from importAmir/CI-CBM, is pointer only (licence: NONE) · get_code("892d44d97047a10d")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Trustworthy-ML-Lab/Label-free-CBM when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

cos_similarity_cubed_single Ran
ran; our contract draft was wrong, not the code
Trustworthy-ML-Lab/Label-free-CBM/similarity.py
pointer only (licence: NONE); the stored copy get_code serves, from importAmir/CI-CBM, is pointer only (licence: NONE) · get_code("cf659682a960fdc0")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Trustworthy-ML-Lab/Label-free-CBM when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

format_value Ran
ran; our contract draft was wrong, not the code
Trustworthy-ML-Lab/Label-free-CBM/plots.py
pointer only (licence: NONE) · get_code("977ef28dbc4a682a")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Trustworthy-ML-Lab/Label-free-CBM when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

get_activation Ran
ran; our contract draft was wrong, not the code
Trustworthy-ML-Lab/Label-free-CBM/utils.py
pointer only (licence: NONE) · get_code("680ec5c6103dc854")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Trustworthy-ML-Lab/Label-free-CBM when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

get_device Ran
ran; our contract draft was wrong, not the code
Trustworthy-ML-Lab/Label-free-CBM/glm_saga/elasticnet.py
pointer only (licence: NONE); the stored copy get_code serves, from Trustworthy-ML-Lab/Linear-Explanations, is pointer only (licence: NONE) · get_code("406014b884a2aaa7")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Trustworthy-ML-Lab/Label-free-CBM when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

get_init_conceptnet Ran
ran; our contract draft was wrong, not the code
Trustworthy-ML-Lab/Label-free-CBM/conceptset_utils.py
pointer only (licence: NONE) · get_code("48f671cc09cab33f")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Trustworthy-ML-Lab/Label-free-CBM when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

get_pairs Ran
ran; our contract draft was wrong, not the code
Trustworthy-ML-Lab/Label-free-CBM/clip/simple_tokenizer.py
pointer only (licence: NONE) · get_code("d919ae32e5e4e616")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Trustworthy-ML-Lab/Label-free-CBM when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

get_save_names Ran
ran on a synthesized input
Trustworthy-ML-Lab/Label-free-CBM/utils.py
pointer only (licence: NONE) · get_code("c6a6eb6a488f7d1a")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Trustworthy-ML-Lab/Label-free-CBM when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

get_similarity_from_activations Ran
ran; our contract draft was wrong, not the code
Trustworthy-ML-Lab/Label-free-CBM/utils.py
pointer only (licence: NONE) · get_code("192f187efaa61625")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Trustworthy-ML-Lab/Label-free-CBM when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

remove_too_long Ran
ran; our contract draft was wrong, not the code
Trustworthy-ML-Lab/Label-free-CBM/conceptset_utils.py
pointer only (licence: NONE) · get_code("00efcf0359457b86")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Trustworthy-ML-Lab/Label-free-CBM when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

soft_threshold Ran
ran, honoured the contract we drafted
Trustworthy-ML-Lab/Label-free-CBM/glm_saga/elasticnet.py
pointer only (licence: NONE); the stored copy get_code serves, from Trustworthy-ML-Lab/Linear-Explanations, is pointer only (licence: NONE) · get_code("bfe4b187a1c5aeaf")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Trustworthy-ML-Lab/Label-free-CBM when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

whitespace_clean Ran
ran; our contract draft was wrong, not the code
Trustworthy-ML-Lab/Label-free-CBM/clip/simple_tokenizer.py
pointer only (licence: NONE); the stored copy get_code serves, from ltpwy/MSCI, is pointer only (licence: NONE) · get_code("9542161e9640b858")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Trustworthy-ML-Lab/Label-free-CBM when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

build_model Not yet run
unverified (harvested, no recorded run)
Trustworthy-ML-Lab/Label-free-CBM/clip/model.py
pointer only (licence: NONE) · get_code("3662e54c46137680")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Trustworthy-ML-Lab/Label-free-CBM when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

get_data Not yet run
unverified (harvested, no recorded run)
Trustworthy-ML-Lab/Label-free-CBM/data_utils.py
pointer only (licence: NONE) · get_code("50160a0b071c120c")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Trustworthy-ML-Lab/Label-free-CBM when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

get_targets_only Not yet run
unverified (harvested, no recorded run)
Trustworthy-ML-Lab/Label-free-CBM/data_utils.py
pointer only (licence: NONE) · get_code("111e91ef3f6b1e38")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Trustworthy-ML-Lab/Label-free-CBM when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

load Not yet run
unverified (harvested, no recorded run)
Trustworthy-ML-Lab/Label-free-CBM/clip/clip.py
pointer only (licence: NONE); the stored copy get_code serves, from liuting20/MaPPER, is pointer only (licence: NONE) · get_code("b91b981015bbf498")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Trustworthy-ML-Lab/Label-free-CBM when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

Also present in other papers' code

Of 19 samples lifted from this paper's linked repositories, 19 carry a function identity and 0 do not. Of the 19 distinct functions with an identity, 11 are also present in other papers whose code we hold (9 with at least one paper dated earlier, 5 the same month, 11 later) and 8 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

FunctionAlso present inEarliest-datedOthers named
get_pairs 258 other papers
169 dated earlier, 5 the same month, 76 later, 7 same year, order not determinable, 1 undated · 4 only as an assembly brick
1802.06474 (2018-02)
A Closed-form Solution to Photorealistic Image Stylization
1803.01128 (2018-03)
Seq2Sick: Evaluating the Robustness of Sequence-to-Sequence Models with Adversarial Examples
1809.00125 (2018-09)
Simple Fusion: Return of the Language Model
and 255 more not named here
whitespace_clean 231 other papers
148 dated earlier, 5 the same month, 70 later, 7 same year, order not determinable, 1 undated · 4 only as an assembly brick
1901.07441 (2019-01)
PadChest: A large chest x-ray image dataset with multi-label annotated reports
2107.06383 (2021-07)
How Much Can CLIP Benefit Vision-and-Language Tasks?
2108.10904 (2021-08)
SimVLM: Simple Visual Language Model Pretraining with Weak Supervision
and 228 more not named here
basic_clean 218 other papers
149 dated earlier, 4 the same month, 57 later, 7 same year, order not determinable, 1 undated · 4 only as an assembly brick
1901.07441 (2019-01)
PadChest: A large chest x-ray image dataset with multi-label annotated reports
2107.06383 (2021-07)
How Much Can CLIP Benefit Vision-and-Language Tasks?
2108.10904 (2021-08)
SimVLM: Simple Visual Language Model Pretraining with Weak Supervision
and 215 more not named here
build_model 119 other papers
80 dated earlier, 2 the same month, 30 later, 5 same year, order not determinable, 2 undated
1809.11096 (2018-09)
Large Scale GAN Training for High Fidelity Natural Image Synthesis
1901.07441 (2019-01)
PadChest: A large chest x-ray image dataset with multi-label annotated reports
2104.14294 (2021-04)
Emerging Properties in Self-Supervised Vision Transformers
and 116 more not named here
load 23 other papers
16 dated earlier, 1 the same month, 4 later, 1 same year, order not determinable, 1 undated
2208.05318 (2022-08)
Generative Action Description Prompts for Skeleton-based Action Recognition
2210.01115 (2022-10)
LASP: Text-to-Text Optimization for Language-Aware Soft Prompting of Vision & Language Models
2212.04501 (2022-12)
Learning Video Representations from Large Language Models
and 20 more not named here
get_device 5 other papers
3 dated earlier, 2 later · 2 only as an assembly brick
2105.04857 (2021-05)
Leveraging Sparse Linear Layers for Debuggable Deep Networks
2308.03685 (2023-08)
Learning Concise and Descriptive Attributes for Visual Recognition
2405.06855 (2024-05)
Linear Explanations for Individual Neurons
and 2 more not named here
soft_threshold 5 other papers
3 dated earlier, 2 later · 2 only as an assembly brick
2105.04857 (2021-05)
Leveraging Sparse Linear Layers for Debuggable Deep Networks
2308.03685 (2023-08)
Learning Concise and Descriptive Attributes for Visual Recognition
2405.06855 (2024-05)
Linear Explanations for Individual Neurons
and 2 more not named here
add_index_to_dataloader 2 other papers
1 dated earlier, 1 later
2105.04857 (2021-05)
Leveraging Sparse Linear Layers for Debuggable Deep Networks
2604.14519 (2026-04)
CI-CBM: Class-Incremental Concept Bottleneck Model for Interpretable Continual Learning
cos_similarity 2 other papers
1 dated earlier, 1 later
2204.10965 (2022-04)
CLIP-Dissect: Automatic Description of Neuron Representations in Deep Vision Networks
2604.14519 (2026-04)
CI-CBM: Class-Incremental Concept Bottleneck Model for Interpretable Continual Learning
cos_similarity_cubed 1 other paper
1 later
2604.14519 (2026-04)
CI-CBM: Class-Incremental Concept Bottleneck Model for Interpretable Continual Learning
cos_similarity_cubed_single 1 other paper
1 later
2604.14519 (2026-04)
CI-CBM: Class-Incremental Concept Bottleneck Model for Interpretable Continual Learning

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Concept Bottleneck Models (CBMs) provide interpretable prediction by introducing an intermediate Concept Bottleneck Layer (CBL), which encodes humanunderstandable concepts to explain models' decision. Recent works proposed to utilize Large Language Models and pre-trained Vision-Language Models to automate the training of CBMs, making it more scalable and automated. However, existing approaches still fall short in two aspects: First, the concepts predicted by CBL often mismatch the input image, raising doubts about the faithfulness of interpretation. Second, it has been shown that concept values encode unintended information: even a set of random concepts could achieve comparable test accuracy to state-of-the-art CBMs. To address these critical limitations, in this work, we propose a novel framework called Vision-Language-Guided Concept Bottleneck Model (VLG-CBM) to enable faithful interpretability with the benefits of boosted performance. Our method leverages off-the-shelf open-domain grounded object detectors to provide visually grounded concept annotation, which largely enhances the faithfulness of concept prediction while further improving the model performance. In addition, we propose a new metric called Number of Effective Concepts (NEC) to control the information leakage and provide better interpretability. Extensive evaluations across five standard benchmarks show that our method, VLG-CBM, outperforms existing methods by at least 4.27% and up to 51.09% on Accuracy at NEC=5 (denoted as ANEC-5), and by at least 0.45% and up to 29.78% on average accuracy (denoted as ANEC-avg), while preserving both faithfulness and interpretability of the learned concepts as demonstrated in extensive experiments 2 .

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2408.01432")
get_code_for_paper("2408.01432")
have("2408.01432")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2408.01432.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2408.01432.svg)](https://syntology.ai/paper/2408.01432)

Connect an agent — have() is free.