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
The paper proposes that two architectural assumptions—(1) attention and MLPs share a key‑value form <phi(S)>U, and (2) components read from an additive residual stream—are sufficient to answer three interpretability questions: component interaction, information routing, and token attribution. By treating these selections as a computational graph, the authors develop Unpack, a backward attribution method that validates interaction scores, recovered routes, and token attribution against established tests across models ranging from 160M to 6.9B parameters. The study also shows that contribution and causal effect can differ, with a recognizable signature in how components change when a task is removed.
By Po-Kai Chen, Aske Plaat, Niki van Stein
NOTAI.AI is an explainable AI-generated text detection system that goes beyond a simple binary label by showing which signals influenced its prediction. It combines sentence-level conditional probability curvature, a neural detector score, and interpretable stylometric and readability features in an XGBoost meta-classifier, and explains predictions using TreeSHAP feature contributions that can be turned into concise natural-language explanations. Evaluated on a balanced subset of RAID, the full model achieves 0.9685 F1 and receives 94.5–98.6% approval from model judges for the faithfulness of its explanations.
By Oleksandr Marchenko Breneur, Adelaide Danilov, Aria Nourbakhsh, Salima Lamsiyah
arXiv:2606. 03885v1 Announce Type: new Abstract: Feature attribution methods explain predictions by assigning importance scores to input features.
By Kieran A. Murphy, Shameen Shrestha
Posted by Nishant Jain, Pre-doctoral Researcher, and Pradeep Shenoy, Research Scientist, Google Research The constantly changing nature of the world around us poses a significant challenge for the development of AI models. Often, models are trained on longitudinal data with the hope that the training data used will accurately represent inputs the model may receive in the future.
By Google AI
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.
By Pietro Barbiero, Giovanni De Felice, Mateo Espinosa Zarlenga, Francesco Giannini, Filippo Bonchi, Mateja Jamnik, Giuseppe Marra, Ruggero Noris