arXiv Machine Learning June 16, 2026 By Anju Chhetri, Pratik Shrestha, Ramesh Rana, Prashnna Gyawali, Binod Bhattarai

When Confidence Lacks Concepts: Interpretable OOD Detection via Representation Perturbations

Read the original on arXiv Machine Learning →

arXiv:2606. 16196v1 Announce Type: new Abstract: Deep neural networks have achieved remarkable performance across medical imaging tasks, yet their tendency to overgeneralize under distributional shifts poses a major obstacle to safe clinical deployment.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.

safety

arXiv AI

Jul 15

Sparse Autoencoders for Interpretable Out-of-Distribution Detection

arXiv:2607. 12094v1 Announce Type: cross Abstract: Reliable detection of out-of-distribution (OOD) samples is crucial for the safe deployment of machine learning models.

By Ayush Karmacharya (Purdue University), Luke Luschwitz (Purdue University), Lucia Romero (Purdue University), Yanan Niu (EPFL), Joseph Campbell (Purdue University)

benchmarks

arXiv Machine Learning

Aug 12

Clarity: The Flexibility-Interpretability Trade-Off in Sparsity-aware Concept Bottleneck Models

arXiv:2601. 21944v3 Announce Type: replace Abstract: The widespread adoption of deep learning models in computer vision has intensified concerns about interpretability.

By Konstantinos P. Panousis, Diego Marcos

computer-vision efficiency multimodal safety

arXiv AI

Jul 10

When Structured Sparse Autoencoders Learn Consistent Concepts Across Modalities

arXiv:2607. 08605v1 Announce Type: cross Abstract: Sparse autoencoders (SAEs) have emerged as a promising technique for mechanistic interpretability by learning a set of sparse latent features in large models, each of which encodes a distinct concept.

By Weiduo Liao, Yunqiao Yang, Ying Wei

llms efficiency multimodal safety

arXiv AI

Jul 7

Interpretable Human-Label-Free Deep Learning for Real-Bogus Classification with Uncertainty Quantification

arXiv:2607. 05393v1 Announce Type: cross Abstract: Time-domain surveys generate many transient candidates, making Real-Bogus classification a critical step in automated discovery pipelines.

By Rapha\"el Bonnet-Guerrini, Bruno Sanchez, Dominique Fouchez, Benjamin Racine, Maya Guy, Mariam Sabalbal, Manal Yassine, Vincenzo Piuri

benchmarks

arXiv Machine Learning

Jun 24

Density-Informed Pseudo-Counts for Calibrated Evidential Deep Learning

arXiv:2602. 01477v2 Announce Type: replace-cross Abstract: Evidential Deep Learning (EDL) is a popular framework for uncertainty-aware classification that models predictive uncertainty via Dirichlet distributions parameterized by neural networks.

By Pietro Carlotti, Nevena Gligi\'c, Arya Farahi

safety

arXiv AI

Jun 24

Evaluating the Interpretability of Sparse Autoencoders with Concept Annotations

arXiv:2606. 24716v1 Announce Type: cross Abstract: Sparse autoencoders (SAEs) are increasingly used to extract interpretable concepts from vision and vision language models, yet existing evaluation methods largely rely on proxy metrics or qualitative inspection rather than measuring semantic correspondence.

By Jonas Klotz, Cassio F. Dantas, Pallavi Jain, Diego Marcos, Beg\"um Demir

llms rag benchmarks safety

Related stories

Sparse Autoencoders for Interpretable Out-of-Distribution Detection

Clarity: The Flexibility-Interpretability Trade-Off in Sparsity-aware Concept Bottleneck Models

When Structured Sparse Autoencoders Learn Consistent Concepts Across Modalities

Interpretable Human-Label-Free Deep Learning for Real-Bogus Classification with Uncertainty Quantification

Density-Informed Pseudo-Counts for Calibrated Evidential Deep Learning

Evaluating the Interpretability of Sparse Autoencoders with Concept Annotations