On the Faithfulness of Post-Hoc Concept Bottleneck Models

• URL: http://arxiv.org/abs/2606.30498v1
• Date: Mon, 29 Jun 2026 16:02:29 GMT
• Title: On the Faithfulness of Post-Hoc Concept Bottleneck Models
• Abstract summary: We study Post-Hoc Concept Bottleneck Models (post-hoc CBMs)<n>CBMs project latent features onto interpretable concept spaces using auxiliary datasets or vision-language models.<n>For example, random concept projections can achieve competitive accuracy despite being semantically meaningless.
• Score: 7.774981803358894
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Human decision-making interprets the world through high-level concepts, such as recognizing a bird by its belly color. To bridge the gap between opaque deep learning representations and human understanding, Post-Hoc Concept Bottleneck Models (post-hoc CBMs) project latent features onto interpretable concept spaces using auxiliary datasets or vision-language models. However, relying on target task accuracy as the primary measure of post-hoc CBM success obscures whether the learned concepts are semantically meaningful or merely predictive artifacts. For example, random concept projections can achieve competitive accuracy despite being semantically meaningless. In this work, we analyze the learned projections directly and identify two failure cases: First, for concept projections learned from auxiliary data, covariate shifts can lead to unfaithful concept representations for the target task. In particular, we provide an upper bound on the error introduced by this shift. Second, systematic label noise in surrogate concept labels generated by vision-language models leads to unfaithful projections. After formalizing these failure modes, we introduce novel metrics that decouple concept faithfulness from predictive accuracy. Our empirical results across real-world and synthetic benchmarks confirm that these metrics identify unfaithful behaviors that standard accuracy-based evaluation fails to detect.

Related papers

• Assessing Reliability of Symbol Detection in Concept Bottleneck Models [3.0509197593879853]
  Concept Bottleneck Models (CBMs) make predictions through human-interpretable symbols.<n>High task accuracy does not guarantee that these symbols are detected faithfully.<n>We study concept-detection reliability by swapping independently trained concept detectors and classification heads.
  arXiv  Detail & Related papers  (2026-06-15T10:38:49Z)
• Towards Fine-Grained and Verifiable Concept Bottleneck Models [11.236280871580155]
  Concept Bottleneck Models (CBMs) offer interpretable alternatives to black-box predictors.<n>Existing CBMs struggle to verify whether predicted concepts correspond to the correct visual evidence.<n>We propose a fine-grained CBM framework that grounds each concept in localized visual evidence.
  arXiv  Detail & Related papers  (2026-05-14T00:08:09Z)
• Credal Concept Bottleneck Models for Epistemic-Aleatoric Uncertainty Decomposition [22.644661427062726]
  Concept Bottleneck Models (CBMs) predict through human-interpretable concepts.<n>CBMs typically output point concept probabilities that conflate epistemic uncertainty and aleatoric uncertainty.<n>We introduce CREDENCE, a framework that decomposes concept uncertainty by construction.
  arXiv  Detail & Related papers  (2026-04-27T08:27:50Z)
• 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)
• Rethinking Concept Bottleneck Models: From Pitfalls to Solutions [53.84388497227224]
  Concept Bottleneck Models (CBMs) ground predictions in human-understandable concepts.<n>CBM-Suite is a methodological framework to address these challenges.
  arXiv  Detail & Related papers  (2026-03-05T19:37:49Z)
• 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)
• On the Fairness, Diversity and Reliability of Text-to-Image Generative Models [68.62012304574012]
  multimodal generative models have sparked critical discussions on their reliability, fairness and potential for misuse.<n>We propose an evaluation framework to assess model reliability by analyzing responses to global and local perturbations in the embedding space.<n>Our method lays the groundwork for detecting unreliable, bias-injected models and tracing the provenance of embedded biases.
  arXiv  Detail & Related papers  (2024-11-21T09:46:55Z)
• 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)
• Interpreting Pretrained Language Models via Concept Bottlenecks [55.47515772358389]
  Pretrained language models (PLMs) have made significant strides in various natural language processing tasks. The lack of interpretability due to their black-box'' nature poses challenges for responsible implementation. We propose a novel approach to interpreting PLMs by employing high-level, meaningful concepts that are easily understandable for humans.
  arXiv  Detail & Related papers  (2023-11-08T20:41:18Z)
• Uncovering Unique Concept Vectors through Latent Space Decomposition [0.0]
  Concept-based explanations have emerged as a superior approach that is more interpretable than feature attribution estimates. We propose a novel post-hoc unsupervised method that automatically uncovers the concepts learned by deep models during training. Our experiments reveal that the majority of our concepts are readily understandable to humans, exhibit coherency, and bear relevance to the task at hand.
  arXiv  Detail & Related papers  (2023-07-13T17:21:54Z)

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.