A framework for analyzing concept representations in neural models

• URL: http://arxiv.org/abs/2605.01381v1
• Date: Sat, 02 May 2026 11:08:10 GMT
• Title: A framework for analyzing concept representations in neural models
• Abstract summary: We study linear concept subspaces along two axes: textitcontainment, which tests if a concept is fully represented in a subspace but not outside it, and textitdisentanglement, which tests for isolation from other concepts.<n>In experiments on both text and speech models, we first highlight that concept subspaces may not be uniquely determined, and discuss the implications for concept subspace analysis.
• Score: 18.72886146851972
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Understanding how neural models represent human-interpretable concepts is challenging. Prior work has explored linear concept subspaces from diverse perspectives, such as probing and concept erasure. We introduce a unified framework to study these subspaces along two axes: \textit{containment}, which tests if a concept is fully represented in a subspace but not outside it, and \textit{disentanglement}, which tests for isolation from other concepts. In experiments on both text and speech models, we first highlight that concept subspaces may not be uniquely determined, and discuss the implications for concept subspace analysis. Then, we compare properties of concept subspaces estimated using five estimators, proposed in different communities. We find that (1) the choice of estimator impacts the containment and disentanglement properties; (2) the state-of-the-art concept erasure method, LEACE, performs well on both testing axes, but still struggles to generalize to unseen data; and (3) in HuBERT speech representations, phone information is both contained and disentangled from speaker information, while speaker information is hard to contain in a compact subspace, despite being disentangled from phones.

Related papers

• A Geometric Unification of Concept Learning with Concept Cones [58.70836885177496]
  Two traditions of interpretability have evolved side by side but seldom spoken to each other: Concept Bottleneck Models (CBMs) and Sparse Autoencoders (SAEs)<n>We show that both paradigms instantiate the same geometric structure.<n>CBMs provide human-defined reference geometries, while SAEs can be evaluated by how well their learned cones approximate or contain those of CBMs.
  arXiv  Detail & Related papers  (2025-12-08T09:51:46Z)
• FaCT: Faithful Concept Traces for Explaining Neural Network Decisions [56.796533084868884]
  Deep networks have shown remarkable performance across a wide range of tasks, yet getting a global concept-level understanding of how they function remains a key challenge.<n>We put emphasis on the faithfulness of concept-based explanations and propose a new model with model-inherent mechanistic concept-explanations.<n>Our concepts are shared across classes and, from any layer, their contribution to the logit and their input-visualization can be faithfully traced.
  arXiv  Detail & Related papers  (2025-10-29T13:35:46Z)
• Explaining Explainability: Recommendations for Effective Use of Concept Activation Vectors [35.37586279472797]
  Concept Vector Activations (CAVs) are learnt using a probe dataset of concept exemplars.<n>We investigate three properties of CAVs: inconsistency across layers, (2) entanglement with other concepts, and (3) spatial dependency.<n>We introduce tools designed to detect the presence of these properties, provide insight into how each property can lead to misleading explanations, and provide recommendations to mitigate their impact.
  arXiv  Detail & Related papers  (2024-04-04T17:46:20Z)
• A Geometric Notion of Causal Probing [85.49839090913515]
  The linear subspace hypothesis states that, in a language model's representation space, all information about a concept such as verbal number is encoded in a linear subspace.<n>We give a set of intrinsic criteria which characterize an ideal linear concept subspace.<n>We find that, for at least one concept across two languages models, the concept subspace can be used to manipulate the concept value of the generated word with precision.
  arXiv  Detail & Related papers  (2023-07-27T17:57:57Z)
• Multi-dimensional concept discovery (MCD): A unifying framework with completeness guarantees [1.9465727478912072]
  We propose Multi-dimensional Concept Discovery (MCD) as an extension of previous approaches that fulfills a completeness relation on the level of concepts. We empirically demonstrate the superiority of MCD against more constrained concept definitions.
  arXiv  Detail & Related papers  (2023-01-27T18:53:19Z)
• Concept Activation Regions: A Generalized Framework For Concept-Based Explanations [95.94432031144716]
  Existing methods assume that the examples illustrating a concept are mapped in a fixed direction of the deep neural network's latent space. In this work, we propose allowing concept examples to be scattered across different clusters in the DNN's latent space. This concept activation region (CAR) formalism yields global concept-based explanations and local concept-based feature importance.
  arXiv  Detail & Related papers  (2022-09-22T17:59:03Z)
• Overlooked factors in concept-based explanations: Dataset choice, concept learnability, and human capability [25.545486537295144]
  Concept-based interpretability methods aim to explain deep neural network model predictions using a predefined set of semantic concepts. Despite their popularity, they suffer from limitations that are not well-understood and articulated by the literature. We analyze three commonly overlooked factors in concept-based explanations.
  arXiv  Detail & Related papers  (2022-07-20T01:59:39Z)
• FALCON: Fast Visual Concept Learning by Integrating Images, Linguistic descriptions, and Conceptual Relations [99.54048050189971]
  We present a framework for learning new visual concepts quickly, guided by multiple naturally occurring data streams. The learned concepts support downstream applications, such as answering questions by reasoning about unseen images. We demonstrate the effectiveness of our model on both synthetic and real-world datasets.
  arXiv  Detail & Related papers  (2022-03-30T19:45:00Z)
• Sparse Subspace Clustering for Concept Discovery (SSCCD) [1.7319807100654885]
  Concepts are key building blocks of higher level human understanding. Local attribution methods do not allow to identify coherent model behavior across samples. We put forward a new definition of concepts as low-dimensional subspaces of hidden feature layers.
  arXiv  Detail & Related papers  (2022-03-11T16:15:48Z)
• Human-Centered Concept Explanations for Neural Networks [47.71169918421306]
  We introduce concept explanations including the class of Concept Activation Vectors (CAV) We then discuss approaches to automatically extract concepts, and approaches to address some of their caveats. Finally, we discuss some case studies that showcase the utility of such concept-based explanations in synthetic settings and real world applications.
  arXiv  Detail & Related papers  (2022-02-25T01:27:31Z)
• Kernelized Concept Erasure [108.65038124096907]
  We propose a kernelization of a linear minimax game for concept erasure. It is possible to prevent specific non-linear adversaries from predicting the concept. However, the protection does not transfer to different nonlinear adversaries.
  arXiv  Detail & Related papers  (2022-01-28T15:45:13Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.