Naming the Concepts Classifiers Rely On: Language-Anchored Decomposition for Faithful Explanation

• URL: http://arxiv.org/abs/2607.07264v1
• Date: Wed, 08 Jul 2026 10:50:04 GMT
• Title: Naming the Concepts Classifiers Rely On: Language-Anchored Decomposition for Faithful Explanation
• Abstract summary: Language-Anchored Decomposition (LAD) is a post-hoc framework that delivers concepts simultaneously named, faithful, and obtained without modifying the model.<n>LAD produces spatially precise explanations that are decision-relevant under both concept insertion and deletion.
• Score: 8.895569370998093
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Deep neural networks are widely deployed in high-stakes visual applications where interpretability is critical, yet existing explanations face a trade-off: post-hoc concept methods recover factors that are faithful to a model's behavior but unnamed, while naming and by-design methods attach human-readable concepts only by retraining or altering the classifier. We propose Language-Anchored Decomposition (LAD), a post-hoc framework that delivers concepts which are simultaneously named, faithful, and obtained without modifying the model. For each class, a large language model proposes a concept vocabulary that CLIP-based similarity maps localize across image regions. Inverting standard non-negative matrix factorization, LAD fixes these language-grounded maps as the coefficient matrix and learns only a concept basis that reconstructs the frozen encoder's activations, so naming becomes a structural constraint and the model's own feature geometry determines which concepts are retained. Removing this anchor preserves accuracy but collapses attribution faithfulness. Across natural-image, scene, and medical-imaging benchmarks, LAD produces spatially precise explanations that are decision-relevant under both concept insertion and deletion, while uniquely providing stable, human-interpretable concept names.

Related papers

• Interpreting Object-Dependent Concept Brittleness in Text-to-Image Diffusion Models [105.53190946111586]
  We term this phenomenon object-dependent concept brittleness.<n>We present an interpretability-oriented framework to audit and minimally correct these failures.<n>We evaluate the proposed framework on style and attribute failure cases across multiple diffusion backbones.
  arXiv  Detail & Related papers  (2026-09-09T09:07:40Z)
• Concept Unlearning via Cross-Attention Activation Projection for Diffusion Models [6.701045531467819]
  Concept unlearning aims to erase a target concept from a pretrained text-to-image diffusion model without retraining.<n>Existing closed-form methods represent the target concept through the text encoder's response to a few short anchor prompts that name it.<n>We propose PURE, a closed-form method that builds the forget and retain bases from per-layer cross-attention activations.
  arXiv  Detail & Related papers  (2026-05-25T12:18:47Z)
• Explaining CLIP Zero-shot Predictions Through Concepts [54.05282304471016]
  We introduce EZPC to explain CLIP's zero-shot predictions through human-understandable concepts.<n>Our method projects CLIP's joint image-text embeddings into a concept space learned from language descriptions.<n>Our approach maintains CLIP's strong zero-shot classification accuracy while providing meaningful concept-level explanations.
  arXiv  Detail & Related papers  (2026-03-30T09:31:33Z)
• A Concept is More Than a Word: Diversified Unlearning in Text-to-Image Diffusion Models [2.124297073085513]
  Concept unlearning is a promising direction for reducing the risks of harmful content generation in text-to-image diffusion models.<n>Existing approaches typically rely on keywords to identify the target concept to be unlearned.<n>We propose Diversified Unlearning, a distributional framework that represents a concept through a set of contextually diverse prompts.
  arXiv  Detail & Related papers  (2026-03-19T11:20:40Z)
• Hierarchical Concept Embedding & Pursuit for Interpretable Image Classification [39.219841379322716]
  Interpretable-by-design models are gaining traction in computer vision because they provide faithful explanations for their predictions.<n>We propose Hierarchical Concept Embedding & Pursuit (HCEP), a framework that induces a hierarchy of concept embeddings in the latent space.<n>We show that HCEP outperforms baselines in concept precision and recall while maintaining competitive classification accuracy.
  arXiv  Detail & Related papers  (2026-02-11T23:53:15Z)
• Concepts from Representations: Post-hoc Concept Bottleneck Models via Sparse Decomposition of Visual Representations [20.859723044900154]
  This paper introduces PCBM-ReD, a novel pipeline that retrofits interpretability onto pretrained opaque models.<n>It achieves state-of-the-art accuracy, narrows the performance gap with end-to-end models, and exhibits better interpretability.
  arXiv  Detail & Related papers  (2026-01-18T08:01:44Z)
• Fine-Grained Erasure in Text-to-Image Diffusion-based Foundation Models [56.35484513848296]
  FADE (Fine grained Attenuation for Diffusion Erasure) is an adjacency-aware unlearning algorithm for text-to-image generative models.<n>It removes target concepts with minimal impact on correlated concepts, achieving a 12% improvement in retention performance over state-of-the-art methods.
  arXiv  Detail & Related papers  (2025-03-25T15:49:48Z)
• CRCE: Coreference-Retention Concept Erasure in Text-to-Image Diffusion Models [19.205261933636645]
  We introduce CRCE, a novel concept erasure framework.<n>By explicitly modelling coreferential and retained concepts semantically, CRCE enables more precise concept removal.<n>Experiments demonstrate that CRCE outperforms existing methods on diverse erasure tasks.
  arXiv  Detail & Related papers  (2025-03-18T13:09:01Z)
• Discover-then-Name: Task-Agnostic Concept Bottlenecks via Automated Concept Discovery [52.498055901649025]
  Concept Bottleneck Models (CBMs) have been proposed to address the 'black-box' problem of deep neural networks. We propose a novel CBM approach -- called Discover-then-Name-CBM (DN-CBM) -- that inverts the typical paradigm. Our concept extraction strategy is efficient, since it is agnostic to the downstream task, and uses concepts already known to the model.
  arXiv  Detail & Related papers  (2024-07-19T17:50:11Z)
• ClassDiffusion: More Aligned Personalization Tuning with Explicit Class Guidance [90.57708419344007]
  We present **ClassDiffusion**, a technique that leverages a **semantic preservation loss** to explicitly regulate the concept space when learning a new concept.<n>Although simple, this approach effectively prevents semantic drift during the fine-tuning process of the target concepts.
  arXiv  Detail & Related papers  (2024-05-27T17:50:10Z)
• Do Concept Bottleneck Models Respect Localities? [14.77558378567965]
  Concept-based explainability methods use human-understandable intermediaries to produce explanations for machine learning models.<n>We assess whether concept predictors leverage "relevant" features to make predictions, a term we call locality.<n>We find that many concept-based models used in practice fail to respect localities because concept predictors cannot always clearly distinguish distinct concepts.
  arXiv  Detail & Related papers  (2024-01-02T16:05:23Z)
• Implicit Concept Removal of Diffusion Models [92.55152501707995]
  Text-to-image (T2I) diffusion models often inadvertently generate unwanted concepts such as watermarks and unsafe images. We present the Geom-Erasing, a novel concept removal method based on the geometric-driven control.
  arXiv  Detail & Related papers  (2023-10-09T17:13:10Z)

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.