arXiv Machine Learning
Less is More: Efficient Black-box Attribution via Minimal Interpretable Subset Selection
Read the original on arXiv Machine Learning →The Flow has not summarised this story yet — read it at arXiv Machine Learning.
Related stories
arXiv AI
Oct 12
Hide and Seek: HIDE Concepts to SEEK explanations for black box models
Hide and Seek (HnS) is a concept‑level attribution method that interprets black‑box vision models without needing model weights or labeled concept datasets. It retrieves concept‑aligned images via a vision‑language model, localizes and masks the concept region, and measures attribution by observing changes in the model’s output. HnS was validated on CelebA and COCO‑Stuff, showing stronger agreement with ground‑truth attributions than existing methods, and was applied to tasks like image captioning and satellite image segmentation where other concept attribution methods fail.
arXiv Machine Learning
Oct 8
For Those Who Believe in Faithfulness: Optimizing the Area Under Insertion and Deletion Curves for Ranking Relative Feature Importance
The paper introduces Ra‑NEM, a method that optimizes the area under insertion and deletion curves to improve the faithfulness of feature importance attributions in machine learning models. By deriving an objective function from faithfulness and approximating its gradient, the authors link insertion curves to top‑k feature selection, enabling a loss function that measures attribution quality. Ra‑NEM, integrated with the neural explanation mask framework, works with any differentiable model, yielding accurate, robust, and fast attributions that outperform existing algorithms on multiple XAI metrics.
arXiv Computer Vision
Aug 25
Where Not to Learn: Prior-Aligned Training with Subset-based Attribution Constraints
arXiv:2602.07008v5 Announce Type: replace Abstract: Reliable models should not only predict correctly, but also base their decisions on acceptable evidence. However, conventional supervised learning...
arXiv AI
Jun 9
Explaining Black-Box Language Models: Learning to Optimize Linguistically-Structured Word Subsets
arXiv:2606. 08497v1 Announce Type: new Abstract: As deep language models (DLMs) are increasingly deployed in high-stakes domains such as healthcare, understanding their decision rationale becomes paramount for ensuring trust, safety, and accountability.
arXiv AI
Jul 15
Representation and Reference Selection in Training-Free Synthetic Image Attribution
arXiv:2607. 12052v1 Announce Type: cross Abstract: Synthetic image attribution aims at identifying the generator responsible for a given AI-generated image.
arXiv Machine Learning
Sep 23
Matryoshka attribution: Learning to attribute language model outputs to representations and weights
Matryoshka Attribution (MAttr) is a mask‑learning method that identifies nested subsets of a language model’s internal components by minimizing downstream loss. It uses a differentiable sigmoid top‑k operator and randomizes sparsity during training to produce an attribution ordering of components. MAttr tops the Mechanistic Interpretability Benchmark leaderboard and can be applied via reinforcement learning to pinpoint weight changes that control behaviors such as refusal in Llama 3.1 8B Instruct, where restoring just 1% of weights removes refusals while preserving capabilities.