Concept Bottleneck Models

Also known as CBM

Overview

Concept Bottleneck Models predict through an intermediate set of meaningful attributes, such as visual features or clinical findings, so people can examine how those concepts contribute to an output. Approaches include supervised concept predictors with simple classifiers, vision-language models that propose concepts, and structured bottlenecks that model concept relations, hierarchies, or spatial locations. The methods are tested in settings such as fine-grained image classification, medical diagnosis, text and graph prediction, and multimodal tasks, with evaluation increasingly examining concept accuracy and interventions as well as task accuracy. A central tension is that incomplete or noisy concepts can hurt predictions, while information leakage can preserve accuracy but make explanations or user interventions unreliable.

Latest papers

92 papers9 papers in the last four weeks, down 18% on the four weeks before. 0.1% of all new papers.

Nov 10, 2026

When Covariance Is Not Enough: Kernel-Based Regularization for Single-Cell Counterfactuals

Counterfactual editing of single cells, predicting how an observed cell would look had one factor been different, enables in-silico screening where experiments are infeasible, but is useful only if the edit is faithful to the individual and not merely to the condition. Concept bottleneck generative models make the effects of interventions interpretable by decomposing a cell's representation into known and unknown factors. Previous work uses a linear cross-covariance penalty to disentangle known and unknown dimensions. We demonstrate that this first-order criterion does not fully separate information when non-linear interactions are present. We first demonstrate the inadequacy of linear cross-factor penalization with simulation experiments with controlled edits and known non-linear covariate effects. We then demonstrate that adding a nonlinear kernel criterion, the normalized Hilbert-Schmidt Independence Criterion, is able to recover the true intervention effects on simulation data. Finally, we apply the non-linear concept bottleneck model to a complex single-cell RNA-seq dataset and find that it improves the ability to generate counterfactual expression profiles of cells under different tissue environments.
Nov 10, 2026

A Concept-Based Interpretable Framework for Clinical Text-based Prediction via Token-Concept Attention without Concept Supervision

Objective: Concept-based interpretation has emerged as a promising approach for explaining blackbox models using human-understandable, high-level concepts. However, most existing methods require annotated concept labels to train the model to identify concepts in the input, and obtaining such annotations in clinical text is often expensive. This study aims to enable concept-based interpretation for language models without concept supervision on clinical prediction tasks. Methods: We propose a novel framework that enables concept-based interpretation without concept supervision through a tailored cross-attention bottleneck. Clinical text and the text descriptions of medical concepts are first tokenized and embedded by a pretrained language model. A cross-attention module then estimates the presence of each concept for each text token, producing concept relevance scores that capture how concepts are involved throughout the note. These scores are pooled and used in a linear prediction layer to model clinical outcomes in an interpretable manner. Results: The performance of the proposed framework was compared against blackbox models across two tasks: chest trauma severity stratification using a private dataset and an in-hospital mortality prediction task using the publicly available MIMIC-III dataset. The proposed framework achieved AUROC values within 0.02 of the corresponding blackbox models. The framework also enabled cohort- and patient-level interpretation, capturing the overall concept importance across the cohort and patient-specific concept contributions. Conclusion: Our proposed framework realizes concept-based interpretation without requiring ground-truth concept presence labels. It improves the transparency of clinical text predictions while maintaining strong performance in clinical prediction tasks.
Nov 7, 2026

Predictive Surprise as Self-Grounding Concept Bottleneck for Interpretable Time Series

Time-series classifiers deployed in risk-sensitive domains must be (1) accurate, (2) interpretable, and (3) able to abstain when evidence is weak. Existing methods do not deliver all 3 at once, and the obstacle is structural, rather than logistical. Meaningful temporal patterns cannot be defined without knowing segment boundaries, yet meaningful boundaries cannot be placed without knowing which patterns to expect. Existing approaches break this circularity by using fixed windows or expert-annotated vocabularies, thereby sacrificing at least one of the 3 properties. We introduce ConceptTime, which closes the loop through a single self-supervised signal. A frozen probabilistic forecaster predicts a distribution over the next observation at every timestep of the sequence. We call the mismatch between its prediction and the realized signal the predictive surprise. This signal both locates segment boundaries and characterizes each resulting segment through the forecaster. Segments are thus grounded by how they behaved relative to expectation, not by what they look like. These summaries cluster into a vocabulary of dynamical regimes that we call concepts. A lightweight head classifies from the concept sequence, and the distance to the nearest concept yields reliability by design. Across 17 public benchmarks, ConceptTime is competitive with state-of-the-art black-box accuracy, beats every interpretable baseline, and retains near-98% accuracy on Epilepsy with 1% of labels. It further remains competitive with softmax, prototype-distance, and SHAP/TimeX/TimeX++ on OOD detection and deletion faithfulness, without a single annotation, language model call, or domain expert. Code is available at: https://github.com/Sachithx/ConceptTime.git.
Nov 2, 2026

PriCBMs: Multi-granular Concept Bottleneck Vision-Language Models for Visual Privacy Recognition

Widespread image sharing on social media has increased the need for visual privacy recognition to identify inadvertently exposed privacy information. However, multi-label visual privacy recognition presents two challenges. First, privacy categories represent high-level semantic attributes and do not have a one-to-one correspondence with visual objects. Different visual objects may involve the same privacy category, while the same type of object may contain different types of privacy-sensitive information. In this setting, direct prediction methods generally lack explicit guidance for identifying category-relevant privacy cues, leaving this process implicit in the learned image-to-label mapping and potentially limiting classification performance. Second, privacy cues are often distributed across image regions and may not be adequately represented by whole-image features. To address these challenges, we propose Privacy Concept Bottleneck Models (PriCBMs). By introducing privacy-related concepts as intermediate semantic representations, PriCBMs first identify category-relevant privacy cues through visual-concept matching and then predict privacy categories based on concept responses. This process makes privacy predictions more interpretable. To improve the quality of these concepts, we design a concept selection strategy based on target-category relevance, cross-category discriminability, and semantic diversity. Meanwhile, we introduce a global-region modeling module to capture localized privacy evidence while retaining global context. Experiments on VISPR and FineViP show that PriCBMs outperform evaluated competitors across all four multi-label metrics. Ablation studies and concept-quality analyses support the effectiveness of the proposed design. Code is available at https://github.com/sun2293674491-dotcom/PriCBMs.
Oct 27, 2026

Drop the Details, Get the Gist: Dynamic Conceptual Representation for Video Recognition

Concept Bottleneck Models (CBMs), which route predictions through a layer of human-interpretable concepts, have substantially improved the interpretability of visual classification by exposing an explicit, language-based rationale for each prediction. Most existing work focuses on static images, and temporal dynamics in videos have been underexplored in conceptual representation. We propose a framework that extends concept-based image recognition to procedural video understanding. It represents a multi-step video as a temporal sequence of segment-level concept score vectors and feeds this sequence into a Transformer encoder to predict the class label. We also explore a way to estimate the contribution of each concept for further interpretability. We evaluated three concept sets of different granularities on cooking and household-activity videos and found that coarser-grained concepts are sufficient for classifying these videos, which implies that fine-grained textual descriptions may be unnecessary.
Oct 25, 2026

Interpretable and Steerable Molecular Graph Generation using Concept Bottlenecks

Deep graph generators (DGGs) largely lack interpretability, which is a significant limitation for one of their most crucial applications, drug discovery, where interpretable and transparent generation could provide greater control over the desirability of generated molecules, thereby reducing trial-and-error in candidate selection. Common approaches to interpretability, such as disentanglement, cannot guarantee that the learned representations are human-interpretable. To address this, we propose incorporating concept bottlenecks into DGGs, allowing users to interpret, debug, and steer the generation process. We show that this consistently improves distributional fidelity (lower FCD), with only modest, non-systematic effects on validity and uniqueness. We further explore Concept Controller, an optimization-based steering approach that has proven to be effective for steerable image generation. We evaluate our approach on a one-shot molecular graph generation framework, though the underlying ideas can be transferred to sequential graph generation as well.
Oct 22, 2026

When Annotation Patterns Are Learned: Skin-Tone Dependence in Dermatology Concepts

Concept bottleneck models (CBMs) let clinicians inspect and correct skin disease diagnoses through clinical concepts, but only if the concept annotations are reliable. We therefore audit the reliability of SkinCon, a widely used dermatology concept dataset, across skin tones. Within the same disease and with near duplicates removed, erythema is annotated far less often on dark than on light skin, with an odds ratio of 0.17. In contrast, hyperpigmentation and hypopigmentation are annotated more often, with odds ratios of 6.2 and 4.5, respectively. We refer to this pattern as tone-dependent concept annotation. An evidential concept model trained on these annotations learns the same pattern and reproduces it on unseen images. Such a model may agree with potential erythema omissions rather than contradict them. Consistent with this, three label error detectors underperform a disease-only baseline at finding erythema that dermatologist captions mention but SkinCon labels as absent. The three detectors are based on confident learning, training dynamics, and the model's own evidential uncertainty. Concept annotations should thus be audited within each subgroup before explanations built on them can be trusted.
Oct 21, 2026

Learning to Measure and Diagnose: A Clinical-Dictionary Radiomic Bottleneck Model for Thyroid Nodule Classification

Thyroid ultrasound supports the assessment of nodule malignancy, but classification predictions often lack evidence linked to familiar clinical descriptions. Radiomics provides explicitly defined measurements that can support such explanations through a clinical dictionary. However, using these measurements as interpretable evidence requires reliable estimation from ultrasound images and preservation of measurement fidelity when optimizing classification performance. We propose a clinical-dictionary radiomic bottleneck model for thyroid nodule classification. Within this model, Family-Aware Radiomic Learning (FARL) estimates measurements with balanced supervision across feature families. Fidelity-Guided Bottleneck Modeling (FGBM) constructs a fixed bottleneck, followed by joint optimization of measurement estimation and classification under fidelity guidance. Decision evidence decomposition then traces feature contributions through a linear classifier and organizes them by clinical dictionary categories. Experiments on ThyroidXL and TN3K show competitive classification performance, while case studies illustrate feature contributions for benign and malignant nodules. These findings indicate interpretable classification with inspectable quantitative evidence informed by clinical knowledge. Code is available online.
Oct 20, 2026

Auditing Where Concept Bottleneck Accuracy Comes From on CUB

Concept Bottleneck Models (CBMs) promise predictions that humans can inspect and correct through concepts such as "curved beak". Yet on CUB-200-2011, their standard benchmark, progress is measured like that of ordinary classifiers: by task and concept accuracy. Neither reveals whether the label is predicted from the exposed concept scores, or whether a concept is supported by visual evidence of that concept rather than by co-occurring features such as cues to the species as a whole. We audit where the accuracy of CBMs and Concept Embedding Models (CEMs) on CUB comes from. The CUB annotations are too noisy to explain it: class-level training labels agree with per-image annotations on only ~82% of image--concept pairs, and classifiers trained on per-image annotations reach only ~37% species accuracy. Leakage probes show that CEM predictions cannot be reconstructed from their concept scores; the missing class information sits in internal embeddings. We identify four design axes through which class information can enter concept scores---receptive field, shared versus concept-specific representations, norm-dependent scoring, and task supervision. An ablation shows that most of it enters through non-local features: restricting a ResNet50 backbone to local BagNet patches lowers the accuracy recoverable from concept scores from 72% to 43%, close to what ground-truth annotations support, while joint training raises it again at the cost of concept accuracy. Localization and occlusion show that locality makes grounding measurable but does not guarantee it: under class-level labels, local concept scores use the head as a proxy for body, wing, and tail concepts, and CEM concept scores barely respond to occluding their supporting part. Task and concept accuracy should thus support, not drive, the evaluation of CBMs, and given the noisy annotations, CUB accuracy gaps should not be overinterpreted.
Oct 16, 2026

Residual Stochastic Concept Bottleneck Models

Concept-based models (CMs) learn human-interpretable intermediate representations that enable users to understand the model's reasoning and steer its predictions through test-time concept interventions. However, in realistic settings, their performance can be limited by concept incompleteness, where the training concepts fail to capture all task-relevant information. Adding an unconstrained residual pathway to the model's predictive process can overcome the consequences of incompleteness. However, this introduces an inscrutable, leak-prone prediction pathway that may weaken concept interventions, as these often leave residual variables unchanged. To address this limitation, we introduce Residual Stochastic Concept Bottleneck Models (Res-SCBMs), a family of concept-based models that jointly model concept and residual variables through a multivariate Gaussian distribution. Res-SCBMs learn a covariance structure that explicitly captures dependencies between the known concepts and learnt residual variables, allowing interventions to propagate to statistically dependent residual variables through Gaussian conditioning. This extends the intervention capabilities of previous CMs without requiring concept completeness during training. Our results show that, across multiple concept-incomplete benchmarks, Res-SCBMs improve predictive performance over competing baselines while retaining effective test-time concept interventions.
Oct 15, 2026

Harmful Partial Interventions and Benign Leakage in Concept-based Models

Artificial intelligence systems deployed in high-risk settings increasingly require models that support meaningful human oversight. Concept-based models (CMs) offer a promising framework by enabling users to inspect and intervene on intermediate, human-understandable concepts. However, concept interventions can counterintuitively worsen downstream predictions, a failure mode we formalise as intervention harm. We distinguish harm after all concepts have been intervened on from harm under partial interventions, the more likely practical use case. Modern CMs often achieve high accuracy by encoding, or leaking, additional task-relevant information in their intermediate concept representations. Recent work argues that such leakage can be benign with respect to intervention harm when concept representations satisfy two conditions: sufficiency and localisation. We prove that these criteria are not sufficient to guarantee that concept interventions improve downstream performance. Across controlled and real-world settings, we find that concept supervision incompleteness is associated with increased intervention harm. Importantly, optimising the model when all concepts are intervened on, a previously proposed leakage mitigation objective, reduces endpoint harm but does not reliably prevent harmful partial corrections. Hence, we introduce a complementary monotonic intervention objective that directly penalises increases in task loss along partial intervention trajectories. Combining endpoint and monotonic intervention training substantially reduces the prevalence and magnitude of partial intervention harm while preserving concept and task predictive performance.
Oct 6, 2026

Beyond Explanation: Debugging Medical Imaging Models via Concept Intervention

Medical imaging models often operate as black boxes, limiting interpretability and systematic debugging. We introduce an easy-to-use, plug-and-play framework for concept-based interpretation and model refinement. By aligning a single-modality encoder to BioMedCLIP, we construct a Concept Bottleneck Model (CBM) that enables concept-level interventions. These interventions allow us to isolate causal versus spuriously correlated concepts, validate insights with domain experts, and generate counterfactual samples for targeted fine-tuning. We evaluate our framework on a Mayo Clinic ultrasound dataset and the CheXpert 5x200 chest X-ray dataset. Results demonstrate that concept intervention enables reliable model diagnosis while maintaining, and occasionally improving predictive performance via guided fine-tuning. Our findings highlight the practical value of this framework for controlled, interpretable refinement of clinical deep learning models.
Oct 6, 2026

AnyBottle: A Recipe to Only Keep the Concepts You Really Need

Concept bottleneck models (CBMs) make predictions inspectable and intervenable by routing them through human-interpretable concepts, but originally required concept annotations. Annotation-free variants remove this requirement, but typically use large concept vocabularies, static at both training and inference, producing bottlenecks larger than any task or prediction needs and harder to inspect. We propose AnyBottle, a single recipe for building compact, task-specific CBMs. AnyBottle assumes only a frozen backbone and an unsupervised concept pool, such as a sparse autoencoder. A black-box teacher trained on the same backbone then guides selection: each round adds the concept that best explains the bottleneck's current failures, with candidates restricted to regions of teacher/student disagreement. Trained with nested dropout over this selection order, the final bottleneck predicts accurately from any concept prefix, so inference spends fewer concepts on inputs it is confident about early and more on hard ones. Since no stage is modality-specific, a new domain and task requires swapping only the backbone and concept pool. Across six vision and two text datasets and two teacher paradigms, AnyBottle yields bottlenecks with fewer concepts and higher concept consistency than annotation-free baselines, while staying close to the black-box reference. Overall, AnyBottle shows that going annotation-free need not mean going large: a small, discovered vocabulary can be as expressive as a much larger, fixed one.
Oct 5, 2026

When Are Concept Bottleneck Model Explanations Faithful and Compact?

Concept bottleneck models (CBMs) are neural classifiers that allow to explain their decisions via high-level concepts, potentially enabling understanding, steering and debugging. However, their explanations are often derived heuristically. Building on formal explainability, we argue they should also be faithful, i.e., not misreport which concepts actually matter. We show that, for widespread CBM architectures, including recent VLM-based variants, faithful explanations must include all concepts in the bottleneck, compromising interpretability when this is large. This result applies to both heuristic and faithful-by-construction formal explanations. To encourage the existence of compact faithful explanations, we suggest i) modeling concepts probabilistically as binary or categorical random variables (rather than logits), and ii) employing per-concept training-time sparsification via group lasso (rather than regular elastic net). We also extend algorithms from formal explainability to CBMs, and show they outperform natural heuristics in terms of guarantees and explanation size. Overall, our work warns against naive interpretability claims and provides formal conditions and practical strategies for ensuring CBMs are as interpretable as advertised.
Oct 1, 2026

EviDent-CBCT: Evidence-Bottlenecked Report Generation from Dental CBCT under Non-Exhaustive Report Supervision

Dento-maxillofacial cone-beam CT (CBCT) reports may contain dozens of tooth-specific, anatomical, and spatial findings from a single 3D scan. Learning to generate such reports from limited clinical data is challenging because routine reports may not exhaustively document image findings, and a non-mention may reflect either absence or non-reporting. We present EviDent-CBCT, an evidence-bottlenecked framework designed for this incomplete supervision. An anatomy-aware network maps each CBCT scan to a discrete record of tooth-level, global, and tooth-IAC evidence. A dental-logic consistency projection reconciles incompatible evidence before a deterministic renderer and an image-blind local language model generate the report using only this record. For tooth-level evidence, reliability-aware training uses eligible non-mentions as reduced-weight negatives, while unreported global and tooth-IAC labels remain unknown. A metal-sensitive input channel preserves intensity cues from dental materials. Across three validation runs, EviDent-CBCT achieves 0.666±0.0060.666\pm0.006 merged evidence set-F1 and 0.402±0.0030.402\pm0.003 RadFact-Lite-Dental logical-F1, versus 0.371±0.0180.371\pm0.018 for the strongest controlled direct baseline. In the ODIN 2026 challenge, it ranked second in automated evaluation and third in blinded clinical Arena comparison on the hidden test set. These results support the discrete evidence record as an effective and auditable interface for CBCT report generation.
Sep 30, 2026

From Speech to Editable Concepts: Probing Emotion Recognition with Concept Bottleneck Models

Speech emotion recognition (SER) is the task of assigning emotion labels to utterances. Early systems relied on acoustic features, whereas recent approaches combine multiple modalities, most commonly speech and text. Still, performance remains poor on many datasets. Large language models (LLMs) have therefore attracted interest for SER, as they can process diverse inputs jointly with instructions. However, direct audio input raises questions of explainability. To address similar questions in image classification, concept bottleneck models were introduced. This work adapts concept bottlenecks to SER to examine how individual predictions depend on transcripts, acoustic descriptions and speaker attributes. Experiments test three LLMs on CREMA-D, IEMOCAP and MELD, with concepts extracted by separate tools. On scripted corpora, LLMs are strongly biased towards the transcript in the zero-shot setting, which lowers Macro-F1 from 27.8 to 5.8 on CREMA-D. Fine-tuning removes this bias, and the transcript raises Macro-F1 from 41.8 to 45.1. Removing speech rate changes 48% of Neutral predictions to Disgust on CREMA-D; removing intensity level on MELD changes predictions despite little change in Macro-F1. These findings show that aggregate performance changes alone do not capture the effects of concept removal on individual predictions.
Sep 29, 2026

Interpretable but Fragile? Robustness of Concept Bottlenecks under Geometric-Semantic Perturbations

Concept Bottleneck Models (CBMs) are designed to provide interpretable intermediate representations, yet how such bottlenecks affect robustness remains unclear, with existing studies reporting mixed and sometimes contradictory findings. We argue that these discrepancies arise from conflating different robustness notions and perturbation regimes, rather than from fundamental disagreements about CBMs themselves. To disentangle these factors, we introduce a generator-based evaluation framework that enables controlled comparisons between standard classifiers and CBMs under two distinct perturbation types: continuous geometric perturbations in latent space and discrete semantic interventions in concept space. Within this framework, we evaluate robustness both empirically, via prediction and concept-level sensitivity metrics, and certifiably, using randomized smoothing in latent and concept spaces. Across experiments, we reconcile previously conflicting findings by clarifying when, and in what sense, concept bottlenecks do or do not improve robustness. By further analyzing robustness under varying task conditions, including class semantic similarity and concept vocabulary size, we show that interpretability does not inherently confer robustness. Instead, concept bottlenecks shift where and how sensitivity manifests, revealing a nuanced interpretability robustness trade off that depends critically on the perturbation regime and task structure. Together, our results show that interpretability and robustness are distinct objectives: interpretable intermediate representations do not uniformly improve robustness, but instead redistribute sensitivity across perturbation spaces and model families.
Sep 29, 2026

Aperture: Training-Free Multiscale Concept Bottlenecks for Remote Sensing

While earth observation models have advanced substantially, they still lack interpretability. While concept-bottleneck models provide interpretability and expert interaction, they are either too expensive to train for the remote sensing domain or perform poorly without annotation. We posit that in expert domains like remote sensing, such training-free models require both fine details in both image and concept space. In image space, we propose a multiscale concept bottleneck using greedy quadtree routing to locate small concepts. In concept space, we replace contrastive vision language models with pre-trained MLLMs and present a way to get reliable concept scores from them. We introduce APERTURE that blends concept scores at the global image and native concept-scale level to give state-ofthe-art training-free model performance. To test these models, introduce SiFC, a fine-grained concept-centric dataset across three countries, with human-reviewed class-level concept maps. On SiFC, APERTURE outperforms the best training-free baselines by more than 10 percentage points in macro F1-score, and notably also outperforms supervised concept bottleneck models. Targeted component-removal tests examine whether concept scores respond to changes in visual evidence, while temporal experiments show that descriptor updates improve recognition of technological changes without retraining.
Sep 29, 2026

CHOQOLATE: Organizing Concept Bottleneck Latent Spaces with Choquet Integrals

Concept Bottleneck Models (CBMs) built on vision-language models such as CLIP represent a latent space as human-understandable concepts. These representations are unfaithful: related concepts are entangled, so individual scores do not reflect their intended meaning. We propose CHOQOLATE, an interpretable-by-design layer based on 2-additive Choquet integrals, which merges correlated concepts into compact nodes. Across four datasets, CHOQOLATE achieves a favorable accuracy-interpretability trade-off, with weight-sparse and semantically coherent nodes. A closed-form gradient derivation, backed by experiments, explains why Choquet layers drive this organization without explicit supervision. Choquet weights also map directly to Shapley values, which enables test-time intervention. On standard bias-mitigation benchmarks, suppressing spurious concepts after training performs on par with methods that require group annotations or retraining, while needing neither.
Sep 28, 2026

DF-CBM: Region-Aware Concept Bottleneck Models for Deepfake Detection

Deepfake detection methods have become increasingly effective yet most provide limited insight into the evidence behind their predictions. However, in forensic settings users also need to know which manipulation cues support the decision and where they appear. Existing explainability methods only partially address this need since localization-based approaches lack semantic descriptions while language-based explanation methods are only weakly grounded in visual evidence. In this work, we propose DF-CBM, a region-aware concept bottleneck model for explainable deepfake detection. DF-CBM builds a compact vocabulary of manipulation-related concepts from textual artifact annotations and links each concept to plausible facial and boundary regions. It then predicts these concepts from visual features using a concept-specific masked attention mechanism guided by parsed facial masks and the final real/fake decision is made from the predicted concept bottleneck. Our experiments show that DF-CBM outperforms concept-based baselines in concept prediction and deepfake classification while remaining competitive with state-of-the-art black-box detectors. Finally, qualitative results and intervention analyses demonstrate that DF-CBM provides spatially grounded concept evidence and enables counterfactual explanations of how individual manipulation concepts influence the final prediction. Our code is available at: https://github.com/GeorgeTsoumplekas/DF-CBM.
Sep 20, 2026

TRACE: Tractable Routing Autoencoder for Clinical ECG

Deep learning has advanced automated electrocardiogram (ECG) diagnosis, but the field's most accurate models, foundation models pretrained on millions of recordings, are not decision-pathway auditable: a clinician cannot trace a diagnosis to a physiological pathway or intervene on one. We propose TRACE, a Tractable Routing Autoencoder for Clinical ECG, whose 32-dimensional clinical latent space is specified in advance from domain knowledge rather than discovered by optimization. TRACE partitions this space into perfusion, structure, and conduction subspaces, routes each to its own diagnostic head by design, regularizes the partition with an orthogonality penalty, and reconstructs the ECG through a decoder that permits latent perturbation. On PTB-XL and Georgia, TRACE exceeds unconstrained classifiers and stays ahead of an ECG foundation model pretrained on ten million recordings, evaluated by linear probe on frozen features, at roughly an eighth of the parameter count. On the nine-label CPSC2018 cohort, which carries no structural class, the framework transfers with only the routing table re-specified to a perfusion/rhythm/conduction partition. Joint probe, erasure, and perturbation analyses verify the routing contract, and perturbing the depolarization and repolarization pathways modulates the reconstructed waveform. Removing the specified partition and its orthogonality penalty costs 1.70 AUC and 11.30 macro-F1 points on PTB-XL, and 2.76 AUC and 16.92 macro-F1 points on Georgia. A capacity-matched permutation control places arbitrary assignments within 0.34 AUC points of the ontology routing and leaves macro-F1 statistically level (p=0.619): the ontology supplies decision-pathway auditability at no macro-F1 cost.
Sep 17, 2026

When Do Language-Grounded Explanations Help? A Graph-Bottleneck for Farm Monitoring Interpretable Sheep Facial Pain

Automated pain recognition from facial expression could make continuous welfare assessment practical in sheep, but adoption depends on trust: a stockperson cannot act on a score that arrives without justification. We ground a model in the Sheep Pain Facial Expression Scale (SPFES) by letting each detected facial region attend over text embeddings of the clinical descriptors and then test whether the resulting explanations mean anything. They do not. Ablating an entire descriptor changes the predicted logit by about 10−410^{-4}, and the most-attended cue agrees with the predicted pain level in only 32.6%32.6\% of regions, although the attention maps, the learned gate, and the generated text all proposed otherwise. We therefore remove the appearance bypass with a concept bottleneck whose classifier reads only SPFES concept scores, supervised by per-region state annotations that image-level pipelines discard. This costs 0.050.05--0.100.10 in Cohen's κκ but yields concepts that are demonstrably learned: minority pain-indicating states are recovered at 3.53.5--8.3×8.3\times their base rates, and the ear and eye severity orderings emerge without severity supervision. Removing the supervision alone leaves κκ unchanged while concept accuracy falls to 0.1090.109, showing that architectural necessity does not imply semantic validity. We also show that pooled concept accuracy is misleading under clinical imbalance and provide a cross-validated, protocol-matched benchmark of seven methods on this dataset.
Sep 15, 2026

How to make effective use of domain experts for image classification?

A lot of expectations have been put for years on integrating domain expert knowledge in image classification models. Several approaches have been explored, Concept Bottleneck Models (CBMs) opened up a new avenue of research leading to many variants, and more recently to Concept-based Embedding Models (CEMs). CBM consider binary encoding of each concept, while CEM expands this idea by embedding each concept through two vectors. However in real-life scenarii, domain experts' knowledge is usually organized in concepts determined by various attributes, each attribute encoded either with numerical values, or range of values, or binary values, or categorical values. In this work, we first finetune an image feature extractor for classifying attributes representing the downstream object classes, where the class attributes have been specified by experts under various encoding formats. A classification head is then learnt from these various attributes to categorize target objects. We experimentally show that it improves the classification for three datasets: Kaggle fish dataset, AWA2 and a more challenging new wood charcoal dataset. We then propose an automatic selection of potential missclassified data. In this second step, experts are asked for those data to eventually modify the predicted attributes in order to improve the classification.
Sep 14, 2026

Concept-Grounded Reasoning with Prompt-Driven Localization for Interpretable Structured Report Generation

Medical imaging modalities such as ultrasound and X-ray are widely used in clinical practice, where diagnosis follows a structured, evidence-driven workflow aligned with standardized criteria. While multimodal large language models (MLLMs) show promise for automated medical report generation, most existing systems rely on end-to-end multimodal fusion without modeling clinically defined intermediate attributes, leading to limited grounding and interpretability. To address this issue, we propose CORAL (COncept-grounded ReAsoning with Localization), a multimodal framework that integrates spatial grounding and concept-level supervision into a unified reasoning process. CORAL employs a prompt-driven medical segmentation model to localize lesions and predicts multi-class clinical attributes through a Concept Bottleneck module. The resulting textual concept tokens are combined with mask-modulated visual features within an MLLM to enable structured report generation and diagnostic prediction. Experiments on BUS-CoT and IU X-ray datasets demonstrate consistent improvements in diagnostic accuracy, concept consistency, and report quality over strong general-purpose and medical MLLMs, indicating that concept-grounded reasoning better aligns generation with clinical decision processes.
Sep 9, 2026

Explainable Prediction from Mobile Sensing Data through LLM-guided Concept Integration

Mobile sensing enables longitudinal monitoring of behavioral and physiological patterns in everyday settings. However, accurate prediction remains challenging in small-cohort health-sensing studies, where task-specific outcome supervision is limited relative to heterogeneous sensing data. Interpretability is also important, as model outputs should reflect meaningful behavioral and physiological patterns rather than predictive scores alone. We develop a Concept-Integrated Transformer (CIT) with LLM-guided concept supervision for explainable prediction from mobile sensing data. CIT uses a pretrained large language model to generate baseline-aware concept abnormality targets with confidence weights without manual concept annotation. Across two longitudinal datasets, CIT achieves the highest F1 score on AFFECT (0.756) and ties for the highest on a PHQ-9 dataset (0.765). The learned concept scores also reveal interpretable behavioral and physiological patterns; in AFFECT, sleep quantity and quality show the clearest difference between high and low negative affect groups. These findings support LLM-guided concept integration for accurate and interpretable prediction in small-cohort mobile sensing studies.
Aug 26, 2026

Are Concept Bottleneck Models Effective as Decision-Support Systems?

Concept Bottleneck Models (CBMs) are interpretable-by-design neural networks that detect human-understandable concepts from the input and use them to generate predictions. By allowing users to inspect the concepts underlying a prediction and explore how predictions change under alternative concept configurations, CBMs have emerged as one of the most prominent approaches to supporting human-AI collaboration. However, user studies investigating their actual effectiveness as decision-support systems remain limited. We present two large-scale user studies (N participants = 705, N observations = 6,959) evaluating how concept-based explanations and user interventions on the model's concepts affect the performance of the human-AI team in two distinct binary classification tasks. Our results show that CBMs, and particularly their interactive component, can improve human-AI team accuracy relative to both unaided human performance and performance with non-interpretable AI support. However, these benefits emerge only under certain conditions: classification tasks perceived as difficult, easily identifiable concepts, and active interaction with the model. We also discuss how inaccurate concept detection may undermine users' trust in the model. Overall, this work provides practical guidance for the deployment of CBMs as effective decision-support tools.
Aug 24, 2026

The Illusion of Control: Why Bare Classifier Inversion Silently Fails in Concept-Bottleneck Text Generation

Concept-bottleneck controllable generation routes multi-attribute control through a low-dimensional concept code that, at deployment, must be synthesised from a target attribute configuration. We study this problem in concept-bottleneck text generation under multi-axis compositional generalisation, comparing three ways to obtain the inference-time code: classifier inversion against the encoder heads, reference-text encoding, and a post-hoc label-conditioned prior. Since a concept code admits no direct LM-fluency term, regularising inversion must instead constrain the code toward the encoder's training distribution. We therefore test bare inversion and three regularised variants: label-agnostic and label-conditioned Mahalanobis penalties, and a conditional normalising-flow density baseline. Every inversion variant we test underperforms a simple post-hoc prior fitted to per-combination encoder means on the same checkpoints, across three backbone families spanning 124124M to 88B parameters. The bare form of classifier inversion also silently collapses to chance, traceable to a directly measured off-manifold code. We validate this diagnosis on real-world benchmarks and under external evaluators, enabling fair comparison with published baselines.
Aug 23, 2026

Weakly supervised concept Bottleneck Learning for Robust Two stage Object centric visual reasoning

Two-stage neuro-symbolic architectures provide an elegant paradigm for visual problem solving by cleanly separating connectionist perception of predefined symbols from possibly later defined relational reasoning thereon. However, anchoring high-level predicates into visual frames typically necessitates annotations that are expensive to acquire. In this work, we introduce the Dynamic Orthogonal Concept Bottleneck (D-OCB), an object-centric slot- VAE framework designed to extract human-aligned symbolic predicates under extremely weak supervision. D-OCB eliminates the arduous manual tuning of loss-balancing coef- ficients by dynamically learning optimal hyperparameter allocations during training. To infuse prior knowledge on independence of concept categories, in addition to standard re- construction self-supervision we penalize correlation across concept subspaces. Crucially, to combat the instability of very low supervision regimes, D-OCB incorporates a dynamic di- mensionality allocation mechanism; this adaptive formulation allows well-represented con- cepts to yield latent dimensions to underperforming concepts that are lagging behind, effectively preventing representation collapse and significantly improving overall concept accuracy. Through an extensive empirical evaluation, we demonstrate that our framework achieves high concept alignment and downstream visual reasoning accuracy using minimal label budgets, matching or outperforming end-to-end paradigms.
Aug 21, 2026

ConceptTS: LLM-Guided Concept Bottlenecks for Interpretable Multivariate Time-Series Forecasting

State-of-the-art multivariate time-series forecasters can model complex temporal and cross-variable dependencies, yet their opaque representations provide limited insight into why a particular forecast is produced. This lack of transparency restricts their use in settings where practitioners must understand and assess the factors underlying a prediction. We introduce ConceptTS, an interpretable forecasting framework that organizes its predictions around named, human-readable concepts. ConceptTS uses a large language model to propose task-relevant concepts and generate executable labeling rules, translating the language model's domain knowledge into direct supervision without costly manual concept annotation. The proposed concepts are organized into three complementary bottlenecks that describe the historical context, local forecast intervals, and the full forecast horizon. A shared decoder combines representations derived from their predicted activations to construct the forecast, making the model's decision process explicit and supporting direct concept-level interventions. Experiments on the Beijing Multi-Site Air Quality dataset show that ConceptTS achieves accuracy competitive with strong black-box baselines while producing semantically meaningful concept activations.
Aug 21, 2026

TRACE: Training-time Report-guided and Clinically Ordered Concept Editing

Breast ultrasound diagnosis relies on clinically meaningful semantic concepts, yet most deep learning methods adopt end-to-end image-to-label paradigms that lack interpretability and robustness. While concept-based approaches offer a promising alternative, they often assume complete annotations or require multimodal inputs at inference, which significantly limits their real-world applicability. To tackle these issues, we propose Training-time Report-guided and Clinically Ordered Concept Editing (TRACE), a training-time report-guided framework that leverages structured radiology reports as privileged concept supervision while enabling image-only diagnosis at test time. TRACE refines image-derived concepts through a teacher-guided editing mechanism within a malignancy-aware ordered concept space. To address incomplete annotations, we introduce Strategic Concept Missing Training (SCMT) and train an image-only self-editor via edit distillation for autonomous concept refinement. Besides, we introduce BUSC, a concept-enriched benchmark linking images, labels, and structured attributes. Experiments across multiple datasets demonstrate that TRACE achieves superior performance and improved cross-domain robustness compared to existing methods.