English
Related papers

Related papers: Towards Best Practices of Activation Patching in L…

200 papers

Prototypical parts-based networks are becoming increasingly popular due to their faithful self-explanations. However, their similarity maps are calculated in the penultimate network layer. Therefore, the receptive field of the prototype…

Computer Vision and Pattern Recognition · Computer Science 2023-08-17 Mikołaj Sacha , Bartosz Jura , Dawid Rymarczyk , Łukasz Struski , Jacek Tabor , Bartosz Zieliński

Skills are a natural unit for describing what a language model can do and how its behavior can be changed. However, existing characterizations rely on human-written taxonomies, textual descriptions, or manual profiling pipelines--all…

Artificial Intelligence · Computer Science 2026-04-21 Feiyang Kang , Mahavir Dabas , Myeongseob Ko , Ruoxi Jia

Language models can behave in unexpected and unsafe ways, and so it is valuable to monitor their outputs. Internal activations of language models encode additional information that could be useful for this. The baseline approach for…

Machine Learning · Computer Science 2025-04-30 Henk Tillman , Dan Mossing

Automated Machine Learning-based systems' integration into a wide range of tasks has expanded as a result of their performance and speed. Although there are numerous advantages to employing ML-based systems, if they are not interpretable,…

Machine Learning · Computer Science 2022-12-08 Ioannis Mollas , Nick Bassiliades , Grigorios Tsoumakas

Large language models (LLMs) exhibit remarkable versatility in adopting diverse personas. In this study, we examine how assigning a persona influences a model's reasoning on an objective task. Using activation patching, we take a first step…

Machine Learning · Computer Science 2025-09-23 Ansh Poonia , Maeghal Jain

Activation steering methods in large language models (LLMs) have emerged as an effective way to perform targeted updates to enhance generated language without requiring large amounts of adaptation data. We ask whether the features…

Computation and Language · Computer Science 2025-11-05 Masha Fedzechkina , Eleonora Gualdoni , Sinead Williamson , Katherine Metcalf , Skyler Seto , Barry-John Theobald

In this report we investigate fundamental requirements for the application of classifier patching on neural networks. Neural network patching is an approach for adapting neural network models to handle concept drift in nonstationary…

Machine Learning · Computer Science 2019-01-17 Sebastian Kauschke , David Hermann Lehmann

Large Language Models such as GPTs (Generative Pre-trained Transformers) exhibit remarkable capabilities across a broad spectrum of applications. Nevertheless, due to their intrinsic complexity, these models present substantial challenges…

Machine Learning · Computer Science 2024-10-17 Ashkan Golgoon , Khashayar Filom , Arjun Ravi Kannan

Current machine learning models are evaluated through behavioral snapshots, with benchmark accuracies, win rates and outcome-based metrics. Model explanations and evaluations, however, are fundamentally intertwined: understanding why a…

Computers and Society · Computer Science 2026-05-08 Isabelle Lee , Emmy Liu , Cathy Jiao , Brihi Joshi , Dani Yogatama , Fazl Barez , Michael Saxon

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

Activation Patching is a method of directly computing causal attributions of behavior to model components. However, applying it exhaustively requires a sweep with cost scaling linearly in the number of model components, which can be…

Machine Learning · Computer Science 2024-03-04 János Kramár , Tom Lieberum , Rohin Shah , Neel Nanda

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

With machine learning models being increasingly used to aid decision making even in high-stakes domains, there has been a growing interest in developing interpretable models. Although many supposedly interpretable models have been proposed,…

Artificial Intelligence · Computer Science 2021-08-17 Forough Poursabzi-Sangdeh , Daniel G. Goldstein , Jake M. Hofman , Jennifer Wortman Vaughan , Hanna Wallach

While deep neural networks have achieved remarkable performance, they tend to lack transparency in prediction. The pursuit of greater interpretability in neural networks often results in a degradation of their original performance. Some…

Computer Vision and Pattern Recognition · Computer Science 2024-08-09 Hefeng Wu , Hao Jiang , Keze Wang , Ziyi Tang , Xianghuan He , Liang Lin

Interpretable machine learning tackles the important problem that humans cannot understand the behaviors of complex machine learning models and how these models arrive at a particular decision. Although many approaches have been proposed, a…

Machine Learning · Computer Science 2019-05-21 Mengnan Du , Ninghao Liu , Xia Hu

As the use of deep learning techniques has grown across various fields over the past decade, complaints about the opaqueness of the black-box models have increased, resulting in an increased focus on transparency in deep learning models.…

Computation and Language · Computer Science 2024-03-19 Siwen Luo , Hamish Ivison , Caren Han , Josiah Poon

Mechanistic interpretability seeks to understand the neural mechanisms that enable specific behaviors in Large Language Models (LLMs) by leveraging causality-based methods. While these approaches have identified neural circuits that copy…

Computation and Language · Computer Science 2023-08-29 Vedant Palit , Rohan Pandey , Aryaman Arora , Paul Pu Liang

While large language models (LLMs) demonstrate remarkable success in multilingual translation, their internal core translation mechanisms, even at the fundamental word level, remain insufficiently understood. To address this critical gap,…

Computation and Language · Computer Science 2026-01-16 Hongbin Zhang , Kehai Chen , Xuefeng Bai , Xiucheng Li , Yang Xiang , Min Zhang

Transformer language models are state of the art in a multitude of NLP tasks. Despite these successes, their opaqueness remains problematic. Recent methods aiming to provide interpretability and explainability to black-box models primarily…

Computation and Language · Computer Science 2022-03-14 Felix Friedrich , Patrick Schramowski , Christopher Tauchmann , Kristian Kersting

Interaction languages such as MSC are often associated with formal semantics by means of translations into distinct behavioral formalisms such as automatas or Petri nets. In contrast to translational approaches we propose an operational…

Software Engineering · Computer Science 2020-05-08 Erwan Mahe , Christophe Gaston , Pascale Le Gall