Interpretable and pedagogical examples

Interpretable machine learning through teaching

We’ve designed a method that encourages AIs to teach each other with examples that also make sense to humans.

The Standard Interpretable Model: A general theory of interpretable machine learning to deductively design interpretable methods using Lagrangian mechanics

arXiv:2606. 12289v1 Announce Type: cross Abstract: As Artificial Intelligence models grow in complexity, interpretability has become an indispensable tool for understanding, debugging, and controlling their computations.

Self-Explanation Tutor for Active Study of CS1 Worked Examples

The paper presents ESSE, a self‑explanation tutor that uses a large language model to give immediate feedback on students’ line‑by‑line explanations of introductory programming worked examples. It evaluates the LLM’s judgments against a domain expert and a crowd of non‑experts, finding that the model is reliable enough to serve as the tutor’s assessment engine. In an introductory Java course, the tutor’s feedback encourages students to persist, improves the completeness and conceptual depth of their explanations, and shows evidence of learning.

Radical AI Interpretability

arXiv:2606. 26523v1 Announce Type: new Abstract: We develop a framework for interpreting AI systems as agents, drawing on the philosophical tradition of radical interpretation and the tools of mechanistic interpretability.

Interpreting "Interpretability" and Explaining "Explainability" in Machine Learning in Physics

arXiv:2606. 26228v1 Announce Type: cross Abstract: We review the concepts of interpretability and explainability as they apply to machine learning in physics.

Teaching models to express their uncertainty in words

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.

AIriskEval-edu Demo: Auditing of Pedagogical Risks in Educational Explanations

arXiv:2607. 25634v1 Announce Type: new Abstract: We present AIriskEval-edu Demo, a platform that audits the pedagogical quality of instructional explanations and provides explainable audit results.

Rethinking LLM-Judged Helpfulness as a Pedagogy Signal: A Pre-Registered Audit Across Tutor Models

LLM tutoring poses a measurement problem: can a general-purpose helpfulness rubric distinguish direct answer-giving from pedagogical guidance? We audit this signal in a pre-registered study.

Actionable Interpretability Must Be Defined in Terms of Symmetries

arXiv:2601. 12913v4 Announce Type: replace Abstract: This paper argues that interpretability research in Artificial Intelligence (AI) is fundamentally ill-posed as existing definitions of interpretability fail to describe how interpretability can be formally tested or designed for.

When Does an Interpretation Count as Established? The Formation, Evaluation, and Responsibility of Interpretation in Generative AI

The paper investigates when an interpretation in generative AI is considered established, arguing that passing local factual checks is insufficient. It introduces three concepts—interpretive appearance, evaluation contract, and standing substitution—to analyze how interpretations gain recognition within sociotechnical processes. The authors propose delayed closure as a practice to keep recognized interpretations revisable and outline five public requirements for transparency, evidence, failure handling, contract revision, and responsibility.

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.