English
Related papers

Related papers: BlackboxNLP-2025 MIB Shared Task: Improving Circui…

200 papers

Mechanistic interpretability (MI) seeks to uncover how language models (LMs) implement specific behaviors, yet measuring progress in MI remains challenging. The recently released Mechanistic Interpretability Benchmark (MIB; Mueller et al.,…

Computation and Language · Computer Science 2025-11-25 Dana Arad , Yonatan Belinkov , Hanjie Chen , Najoung Kim , Hosein Mohebbi , Aaron Mueller , Gabriele Sarti , Martin Tutek

The Circuit Localization track of the Mechanistic Interpretability Benchmark (MIB) evaluates methods for localizing circuits within large language models (LLMs), i.e., subnetworks responsible for specific task behaviors. In this work, we…

How can we know whether new mechanistic interpretability methods achieve real improvements? In pursuit of lasting evaluation standards, we propose MIB, a Mechanistic Interpretability Benchmark, with two tracks spanning four tasks and five…

Mechanistic interpretability work attempts to reverse engineer the learned algorithms present inside neural networks. One focus of this work has been to discover 'circuits' -- subgraphs of the full model that explain behaviour on specific…

Machine Learning · Computer Science 2024-07-12 Joseph Miller , Bilal Chughtai , William Saunders

Many recent language model (LM) interpretability studies have adopted the circuits framework, which aims to find the minimal computational subgraph, or circuit, that explains LM behavior on a given task. Most studies determine which edges…

Machine Learning · Computer Science 2024-07-16 Michael Hanna , Sandro Pezzelle , Yonatan Belinkov

*Automated circuit discovery* is a central tool in mechanistic interpretability for identifying the internal components of neural networks responsible for specific behaviors. While prior methods have made significant progress, they…

Machine Learning · Computer Science 2026-02-20 Itamar Hadad , Guy Katz , Shahaf Bassan

The circuits framework in mechanistic interpretability aims to identify causally important sparse subgraphs of model components, typically evaluated by measuring necessity and sufficiency. We measure circuit reuse, the proportion of…

Computation and Language · Computer Science 2026-05-12 Michael Li , Nishant Subramani

Mechanistic Interpretability (MI) aims to reverse-engineer model behaviors by identifying functional sub-networks. Yet, the scientific validity of these findings depends on their stability. In this work, we argue that circuit discovery is…

Machine Learning · Computer Science 2026-02-04 Maxime Méloux , François Portet , Maxime Peyrard

Understanding how neural networks arrive at their predictions is essential for debugging, auditing, and deployment. Mechanistic interpretability pursues this goal by identifying circuits - minimal subnetworks responsible for specific…

Artificial Intelligence · Computer Science 2026-03-03 Alaa Anani , Tobias Lorenz , Bernt Schiele , Mario Fritz , Jonas Fischer

Transparency of neural networks' internal reasoning is at the heart of interpretability research, adding to trust, safety, and understanding of these models. The field of mechanistic interpretability has recently focused on studying…

Artificial Intelligence · Computer Science 2026-04-17 Nina Żukowska , Wolfgang Stammer , Bernt Schiele , Jonas Fischer

Most of the work on interpretable machine learning has focused on designing either inherently interpretable models, which typically trade-off accuracy for interpretability, or post-hoc explanation systems, which lack guarantees about their…

Machine Learning · Computer Science 2019-06-05 Gregory Plumb , Maruan Al-Shedivat , Eric Xing , Ameet Talwalkar

Mechanistic interpretability (MI) aims to understand AI models by reverse-engineering the exact algorithms neural networks learn. Most works in MI so far have studied behaviors and capabilities that are trivial and token-aligned. However,…

Machine Learning · Computer Science 2024-07-15 Satvik Golechha , James Dao

Mechanistic interpretability aims to understand neural networks by identifying which learned features mediate specific behaviors. Attribution graphs reveal these feature pathways, but interpreting them requires extensive manual analysis --…

Computation and Language · Computer Science 2025-11-11 Giuseppe Birardi

Mechanistic interpretability (MI) is an emerging framework for interpreting neural networks. Given a task and model, MI aims to discover a succinct algorithmic process, an interpretation, that explains the model's decision process on that…

Machine Learning · Computer Science 2026-04-01 Alan Sun , Mariya Toneva

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 powerful learning tools…

Optimization and Control · Mathematics 2024-01-19 Giulia Di Teodoro , Marta Monaci , Laura Palagi

Interpreting language models often involves circuit analysis, which aims to identify sparse subnetworks, or circuits, that accomplish specific tasks. Existing circuit discovery algorithms face a fundamental trade-off: attribution patching…

Machine Learning · Computer Science 2025-10-07 Hao Gu , Vibhas Nair , Amrithaa Ashok Kumar , Jayvart Sharma , Ryan Lagasse

With the dramatic advances in deep learning technology, machine learning research is focusing on improving the interpretability of model predictions as well as prediction performance in both basic and applied research. While deep learning…

Machine Learning · Computer Science 2024-01-24 Shunsuke Kitada

Automated interpretability research has recently attracted attention as a potential research direction that could scale explanations of neural network behavior to large models. Existing automated circuit discovery work applies activation…

Machine Learning · Computer Science 2023-11-21 Aaquib Syed , Can Rager , Arthur Conmy

Through considerable effort and intuition, several recent works have reverse-engineered nontrivial behaviors of transformer models. This paper systematizes the mechanistic interpretability process they followed. First, researchers choose a…

Machine Learning · Computer Science 2023-10-31 Arthur Conmy , Augustine N. Mavor-Parker , Aengus Lynch , Stefan Heimersheim , Adrià Garriga-Alonso

Interpretable machine learning offers insights into what factors drive a certain prediction of a black-box system. A large number of interpreting methods focus on identifying explanatory input features, which generally fall into two main…

Machine Learning · Computer Science 2023-06-02 Vy Vo , Van Nguyen , Trung Le , Quan Hung Tran , Gholamreza Haffari , Seyit Camtepe , Dinh Phung
‹ Prev 1 2 3 10 Next ›