arXiv AI

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.

arXiv AI

Jun 26

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.

By Daniel A. Herrmann, Benjamin A. Levinstein

agents safety

arXiv Machine Learning

Jun 18

From Mechanistic to Compositional Interpretability

arXiv:2605. 08934v2 Announce Type: replace Abstract: Mechanistic interpretability aims to explain neural model behaviour by reverse-engineering learned computational structure into human-understandable components.

By Ward Gauderis, Thomas Dooms, Steven T. Homer, Kola Ayonrinde, Geraint A. Wiggins

safety

arXiv Machine Learning

Jun 26

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.

By Rikab Gambhir, Luisa Lucie-Smith, Jesse Thaler

safety

arXiv AI

Jun 15

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.

By Pietro Barbiero, Mateo Espinosa Zarlenga, Francesco Giannini, Alberto Termine, Filippo Bonchi, Mateja Jamnik, Giuseppe Marra

safety

arXiv Machine Learning

Jul 2

The Model Organism Lottery: Model Organism Interpretability Strongly Depends on Training Methodology

arXiv:2607. 01033v1 Announce Type: new Abstract: Model organisms (MOs) - language models trained to exhibit undesired or unnatural behaviours - are frequently used as testbeds for evaluating white-box interpretability techniques.

By Andrzej Szablewski, Gabriel Konar-Steenberg, Raffaello Fornasiere, Nikita Menon, Stefan Heimersheim

llms reinforcement-learning fine-tuning benchmarks safety

arXiv AI

Jul 17

Towards a Unified Multidimensional Explainability Metric: Evaluating Trustworthiness in AI Models

arXiv:2607. 14315v1 Announce Type: cross Abstract: In this paper, we present a comprehensive framework for assessing the explainability of various XAI methods, such as LIME and SHAP, across multiple datasets and machine learning models, with the ultimate goal of creating a unified multidimensional explainability score.

By Georgios Makridis, Georgios Fatouros, Athanasios Kiourtis, Dimitrios Kotios, Vasileios Koukos, Dimosthenis Kyriazis, Jonh Soldatos

rag benchmarks

arXiv Machine Learning

Jun 10

Compile Once, Differentiate Everywhere: A Differentiable Meta-Circular Interpreter

arXiv:2606. 09930v1 Announce Type: cross Abstract: The boundary between program execution and gradient-based optimization has long limited the use of code itself as a learnable scientific model.

By Lucas Sheneman

llms

arXiv AI

Jul 16

AIMO Interpretability Challenge

arXiv:2607. 13899v1 Announce Type: new Abstract: We propose the AIMO Interpretability Challenge, a competition on distinguishing robust from spurious reasoning in frontier mathematical language models based on the models' internal mechanisms.

By Michal \v{S}tef\'anik, Philipp Mondorf, Andreas Waldis, Qianying Liu, Chuan Yang, Michal Spiegel, Josef Kucha\v{r}, Marek Kadl\v{c}\'ik, Adam Vawda-Oomerjee, Chaoran Liu, Simon Frieder, Barbara Plank, Fazl Barez, Pontus Stenetorp

llms benchmarks safety

arXiv Machine Learning

Jun 16

Evaluating Local Explainability Metrics for Machine Learning Models on Tabular Data

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.

By Tom\'as Pereira, Jo\~ao Vitorino, Eva Maia, Isabel Pra\c{c}a

benchmarks

arXiv AI

Jul 24

DN-Hypo-Pipeline: An AI-Driven Workflow for Generating Hypotheses using Large Language Models and Scientific Explanations

arXiv:2606. 08532v5 Announce Type: replace Abstract: Modern artificial intelligence excels at prediction but cannot explain.

By Lei Lin, Xinlong Pan, Ronghao Wang, Chunbao Zhou, Jue Wang, Yangang Wang, Ivana Rasovska

llms

arXiv Machine Learning

Jun 11

Anatomy of Post-Training: Using Interpretability to Characterize Data and Shape the Learning Signal

arXiv:2606. 12360v1 Announce Type: new Abstract: Language-model post-training is the main stage at which model behavior is shaped, yet it still largely involves optimization of scalar rewards that summarize diverse desiderata.

By Leon Bergen, Usha Bhalla, Sidharth Baskaran, Max Loeffler, Raphael Sarfati, Dhruvil Gala, Ryan Panwar, Santiago Aranguri, Thomas Fel, Atticus Geiger, Matthew Kowal, Siddharth Boppana, Daniel Balsam, Owen Lewis, Jack Merullo, Thomas McGrath, Ekdeep Singh Lubana

safety

arXiv AI

Jun 9

An Alternative Trajectory for Generative AI

arXiv:2603. 14147v2 Announce Type: replace Abstract: The generative artificial intelligence (AI) ecosystem is undergoing rapid transformations that threaten its sustainability.

By Margarita Belova, Yuval Kansal, Yihao Liang, Jiaxin Xiao, Niraj K. Jha

llms agents

Related stories