--> 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. 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.
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.
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.
arXiv:2606. 03885v1 Announce Type: new Abstract: Feature attribution methods explain predictions by assigning importance scores to input features.
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.
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:2607. 04222v1 Announce Type: new Abstract: Interpretability methods aim to reveal the features represented inside large language models (LLMs).
What exactly does word2vec learn, and how? Answering this question amounts to understanding representation learning in a minimal yet interesting language modeling task.
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.
Posted by Amirkeivan Mohtashami, Research Intern, and Florian Hartmann, Software Engineer, Google Research Large language models (LLMs) have significantly improved the state of the art for solving tasks specified using natural language, often reaching performance close to that of people. As these models increasingly enable assistive agents, it could be beneficial for them to learn effectively from each other, much like people do in social settings, which would allow LLM-based agents to improve each other’s performance.
The paper introduces the concept of xeno-interpretability, which studies internal distinctions in large language models that lack corresponding human concepts. It distinguishes between human‑interpretable and xeno‑semantic spaces, showing that LLMs possess a far larger internal representational space than can be captured by finite human descriptions. The authors propose an empirical program to identify and characterize these xeno‑representations, noting their potential to influence model behavior in ways that are not fully visible through human‑readable communication.
arXiv:2606. 28615v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly deployed in high-stakes domains, where free-text explanations such as chain-of-thought and post-hoc rationales are used to justify model outputs.