Interpretable machine learning through teaching

Challenges in Evaluating Explanation Methods for Static and Evolving Data

arXiv:2608. 06351v1 Announce Type: new Abstract: This paper addresses the limitations of Explainable Artificial Intelligence (XAI) with respect to insufficient evaluation.

Rule of Thumb: Explaining Artificial Intelligence Systems using Partial Information

arXiv:2608. 10766v1 Announce Type: new Abstract: Explainable Artificial Intelligence (XAI) seeks to explain how an Artificial Intelligence (AI) system arrived at a particular decision.

Teaching AI to see the world more like we do

Our new paper analyzes the important ways AI systems organize the visual world differently from humans.

From Interpretability Methods to Interpretable Models

The paper argues that explainable AI for computer vision has focused too much on developing interpretability methods rather than assessing how interpretable the models themselves are. It proposes a shift toward model-centric evaluation, using existing tools to compare what different models represent and compute, and emphasizes the need to measure whether humans can truly understand these models. The authors review the current toolbox, survey limited model comparison work, draw parallels to systems neuroscience, and outline a future agenda for model-focused XAI.

When AI art has no author: Study finds generated images often can’t be traced to training data

A new method for surgically removing training examples from a model reveals that as datasets grow, the link between what a model learns and what it produces dissolves.

Diverse by Design: Architectural Constraints for Prototype-Based Interpretability

arXiv:2609.27194v1 Announce Type: new Abstract: Prototype-based neural networks provide inherent interpretability through case-based reasoning, yet suffer from critical limitations: prototypes conver...

Explaining is Harder Than Predicting Alone: Evaluating Concept-based Explanations of MLLMs as ICL Visual Classifiers

arXiv:2605. 28215v2 Announce Type: replace Abstract: In-context learning (ICL) enables multimodal large language models (MLLMs) to classify images from a few labelled examples.

Interpretable and pedagogical examples

Which one is banana man? Evaluating vision-language models in multi-turn pragmatic interpretation

The study examines how vision‑language models handle multi‑turn pragmatic interpretation in iterated reference games, where participants repeatedly identify novel referents using language. Researchers compared human performance with that of several models, manipulating context by varying its amount, order, and relevance. While humans consistently performed well, the models could use prior context but struggled to build relevant context for effective interpretation, indicating missing core skills for efficient linguistic collaboration.

A Definition of Good Explanations and the Challenges Explaining LLM Outputs

arXiv:2606. 14838v1 Announce Type: new Abstract: How to define a good explanation is a long-standing philosophical debate which has found recent renewed interest in the context of AI outputs.

Beyond Simple Input-Output Assessment Tasks: Leveraging Automated Programming Assessment for Non-Trivial Courses

The article discusses how machine learning exercises can be designed for automated assessment tools, framing them as deterministic input-output tasks. It emphasizes that this approach does not create a new grading system but enables existing platforms (e.g., VPL for Moodle, Codeforces, MOJ) to support AI education more effectively. The authors argue that integrating theory with practice through such exercises can foster dynamic, interactive AI courses.

Inside the Visual Mind: Neuroscience-Motivated Concept Circuits for Interpreting and Steering Vision Transformers

arXiv:2606. 06664v1 Announce Type: cross Abstract: Despite high accuracy, Vision Transformer (ViT) predictions can be driven by spurious cues, raising the need to understand their inner workings before safe deployment.