paper-with-me

홈 › Papers

Unboxing the Black Box: Mechanistic Interpretability for Algorithmic Understanding of Neural Networks

2025-11-24 · Bianka Kowalska, Halina Kwaśnicka arxiv

The black box nature of deep neural networks poses a significant challenge for the deployment of transparent and trustworthy artificial intelligence (AI) systems. With the growing presence of AI in society, it becomes increasingly important to develop methods that can explain and interpret the decisions made by these systems. To address this, mechanistic interpretability (MI) emerged as a promising and distinctive research program within the broader field of explainable artificial intelligence (XAI). MI is the process of studying the inner computations of neural networks and translating them into human-understandable algorithms. It encompasses reverse engineering techniques aimed at uncovering the computational algorithms implemented by neural networks. In this article, we propose a unified taxonomy of MI approaches and provide a detailed analysis of key techniques, illustrated with concrete examples and pseudo-code. We contextualize MI within the broader interpretability landscape, comparing its goals, methods, and insights to other strands of XAI. Additionally, we trace the development of MI as a research area, highlighting its conceptual roots and the accelerating pace of recent work. We argue that MI holds significant potential to support a more scientific understanding of machine learning systems -- treating models not only as tools for solving tasks, but also as systems to be studied and understood. We hope to invite new researchers into the field of mechanistic interpretability.

📄 PDF Abstract BibTeX arXiv:2511.19265

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

MINAR: Mechanistic Interpretability for Neural Algorithmic Reasoning

2026-02-24 · Jesse He, Helen Jenne, Max Vargas, Davis Brown 외 arxiv

The recent field of neural algorithmic reasoning (NAR) studies the ability of graph neural networks (GNNs) to emulate classical algorithms like Bellman-Ford, a phenomenon known as algorithmic alignment. At the same time,…

Opening the AI black box: program synthesis via mechanistic interpretability

2024-02-07 · Eric J. Michaud, Isaac Liao, Vedang Lad, Ziming Liu 외

We present MIPS, a novel method for program synthesis based on automated mechanistic interpretability of neural networks trained to perform the desired task, auto-distilling the learned algorithm into Python code. We tes…

Program SynthesisSymbolic Regression

How does GPT-2 Predict Acronyms? Extracting and Understanding a Circuit via Mechanistic Interpretability

2024-05-07 · Jorge García-Carrasco, Alejandro Maté, Juan Trujillo

Transformer-based language models are treated as black-boxes because of their large number of parameters and complex internal interactions, which is a serious safety concern. Mechanistic Interpretability (MI) intends to …

Prediction

Towards a Mechanistic Understanding of Large Reasoning Models: A Survey of Training, Inference, and Failures

2026-01-11 · Yi Hu, Jiaqi Gu, Ruxin Wang, Zijun Yao 외 arxiv

Reinforcement learning (RL) has catalyzed the emergence of Large Reasoning Models (LRMs) that have pushed reasoning capabilities to new heights. While their performance has garnered significant excitement, exploring the …

Reinforcement Learning

Unboxing Tree Ensembles for interpretability: a hierarchical visualization tool and a multivariate optimal re-built tree

2023-02-15 · Giulia Di Teodoro, Marta Monaci, Laura Palagi

The interpretability of models has become a crucial issue in Machine Learning because of algorithmic decisions' growing impact on real-world applications. Tree ensemble methods, such as Random Forests or XgBoost, are pow…

feature selection