The paper demonstrates that the interpretability method known as susceptibilities, originally used for neural networks, can detect algorithmic structure in Turing machines by examining the local loss landscape of a learning problem for noisy Turing machines. It proves that symmetries and path separation in a Turing machine’s algorithm produce permutation symmetries and low‑rank blocks in the susceptibility matrix. Empirical studies on deterministic finite automata show that algorithmic features can be recovered through principal component analysis and clustering in susceptibility space.
arXiv:2511. 09432v2 Announce Type: replace Abstract: Machine learning (ML) models achieve remarkable performance but remain hard to interpret due to their scale and complexity.
arXiv:2609.15533v1 Announce Type: cross Abstract: Mechanistic interpretability has become the dominant lens for understanding frontier language models, as their inner workings are complex and inheren...
arXiv:2607. 26344v1 Announce Type: new Abstract: A gradient-based GNN explainer given a molecule with two chemically equivalent nitro groups assigns them attribution scores that are equal to the last bit.
arXiv:2606. 11319v1 Announce Type: new Abstract: Learning from imperfect data is a central theme in machine learning, connecting practical questions of robustness to fundamental questions of learnability.
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.
arXiv:2606. 28947v1 Announce Type: cross Abstract: In this study we present a formal definition of large discrete sets having, informally, three properties: their elements are easily recognized, easily generated, and the latter tasks are easily learned from examples.
arXiv:2605. 27618v2 Announce Type: replace Abstract: Despite the wide use of explainability techniques to attempt to understand the behavior of Artificial Intelligence (AI), the generated explanations may not always be reliable.
arXiv:2606. 26228v1 Announce Type: cross Abstract: We review the concepts of interpretability and explainability as they apply to machine learning in physics.
arXiv:2605. 06938v2 Announce Type: replace-cross Abstract: Recently Brown et al.
--> Understanding the behavior of complex machine learning systems, particularly Large Language Models (LLMs), is a critical challenge in modern artificial intelligence. Interpretability research aims to make the decision-making process more transparent to model builders and impacted humans, a step toward safer and more trustworthy AI.
arXiv:2606. 07998v1 Announce Type: cross Abstract: Recent advances in generative AI, especially powerful Large Language Models (LLMs) and Large Reasoning Models (LRMs), raise concerns over the interpretability, safety and sustainability of these large and opaque AI models.
arXiv:2601. 22594v2 Announce Type: replace-cross Abstract: The high-level concepts that a neural network uses to perform computation need not be aligned to individual neurons (Smolensky, 1986).