paper-with-me

홈 › Papers

Concepts Worth Having: Refining VLM-Guided Concept Bottleneck Models with Minimal Annotations

2026-05-13 · Nicola Debole, Andrea Passerini, Stefano Teso, Andrea Pugnana, Emanuele Marconato arxiv

Concept-bottleneck models (CBMs) are neural classifiers that compute predictions from high-level concepts extracted from the input. CBMs ensure stakeholders can understand the concepts -- and the predictions they entail -- by learning these from concept-level annotations, which are however seldom available. Recent CBM architectures work around this issue by obtaining annotations from Vision-Language Models (VLMs). While greatly broadening applicability, doing so can yield lower quality concepts and therefore less interpretable models. We strike for a middle ground by introducing Vision-plus-Human-guided CBM (VH-CBM), a hybrid approach that exploits both VLMs and a small amount of dense annotations. VH-CBM employs a Gaussian Process in the VLM's embedding space, which captures useful global information about the target domain, to propagate the expert's supervision to any target data point. Our empirical evaluation shows how VH-CBM predicts more accurate concepts than VLM-guided CBMs even when annotating as little as 1% of the data, while sporting better concept calibration and supporting active learning.

📄 PDF Abstract BibTeX arXiv:2605.16405

Code (0)

등록된 구현이 없습니다.

Tasks

Active Learning

Similar Papers 제목 키워드 기반

Attributing Learned Concepts in Neural Networks to Training Data

2023-10-04 · Nicholas Konz, Charles Godfrey, Madelyn Shapiro, Jonathan Tu 외

By now there is substantial evidence that deep learning models learn certain human-interpretable features as part of their internal representations of data. As having the right (or wrong) concepts is critical to trustwor…

Fairness and Diversity in Information Access Systems

2023-05-16 · Lorenzo Porcaro, Carlos Castillo, Emilia Gómez, João Vinagre

Among the seven key requirements to achieve trustworthy AI proposed by the High-Level Expert Group on Artificial Intelligence (AI-HLEG) established by the European Commission (EC), the fifth requirement ("Diversity, non-…

DiversityFairnessRecommendation Systems

ConceptSMILE: Auditing the Trustworthiness of Concept-Based Explainable AI

2026-07-10 · Mohadeseh Mollapour, Koorosh Aslansefat, Zeinab Dehghani, Bhupesh Kumar Mishra 외 arxiv

Concept-based explainable artificial intelligence (AI) can make model reasoning more human-understandable, but concept-level outputs are not automatically trustworthy. We introduce ConceptSMILE, a model-agnostic perturba…

Process-Guided Concept Bottleneck Model

2026-01-15 · Reza M. Asiyabi, SEOSAW Partnership, Steven Hancock, Casey Ryan arxiv

Concept Bottleneck Models (CBMs) improve the explainability of black-box Deep Learning (DL) by introducing intermediate semantic concepts. However, standard CBMs often overlook domain-specific relationships and causal me…

Density Estimation

On the Concept Trustworthiness in Concept Bottleneck Models

2024-03-21 · Qihan Huang, Jie Song, Jingwen Hu, Haofei Zhang 외

Concept Bottleneck Models (CBMs), which break down the reasoning process into the input-to-concept mapping and the concept-to-label prediction, have garnered significant attention due to their remarkable interpretability…