English
Related papers

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

200 papers

As AI systems are used in high-stakes applications, ensuring interpretability is crucial. Mechanistic Interpretability (MI) aims to reverse-engineer neural networks by extracting human-understandable algorithms to explain their behavior.…

Machine Learning · Computer Science 2025-03-03 Maxime Méloux , Silviu Maniu , François Portet , Maxime Peyrard

How interpretable are the features of leading vision models? The question is increasingly pressing as these models move from research benchmarks into high-stakes deployments, yet existing methods cannot answer it reliably. We close this gap…

Computer Vision and Pattern Recognition · Computer Science 2026-05-21 Julien Colin , Lore Goetschalckx , Nuria Oliver , Thomas Serre

For machine learning models to be most useful in numerous sociotechnical systems, many have argued that they must be human-interpretable. However, despite increasing interest in interpretability, there remains no firm consensus on how to…

Machine Learning · Computer Science 2021-02-03 Andrew Slavin Ross , Nina Chen , Elisa Zhao Hang , Elena L. Glassman , Finale Doshi-Velez

Interpretability research aims to bridge the gap between empirical success and our scientific understanding of the inner workings of large language models (LLMs). However, most existing research focuses on analyzing a single mechanism, such…

Computation and Language · Computer Science 2024-06-10 Francesco Ortu , Zhijing Jin , Diego Doimo , Mrinmaya Sachan , Alberto Cazzaniga , Bernhard Schölkopf

The internal functional behavior of trained Deep Neural Networks is notoriously difficult to interpret. Activation-maximization approaches are one set of techniques used to interpret and analyze trained deep-learning models. These consist…

Machine Learning · Computer Science 2023-06-14 Geraldin Nanfack , Alexander Fulleringer , Jonathan Marty , Michael Eickenberg , Eugene Belilovsky

Transformer-based models have become state-of-the-art tools in various machine learning tasks, including time series classification, yet their complexity makes understanding their internal decision-making challenging. Existing…

Machine Learning · Computer Science 2025-11-27 Matīss Kalnāre , Sofoklis Kitharidis , Thomas Bäck , Niki van Stein

Large language models (LLMs) aligned for safety through techniques like reinforcement learning from human feedback (RLHF) often exhibit emergent deceptive behaviors, where outputs appear compliant but subtly mislead or omit critical…

Machine Learning · Computer Science 2025-07-15 Santhosh Kumar Ravindran

Large language models (LLMs) have achieved remarkable capabilities across diverse tasks, yet their internal decision-making processes remain largely opaque. Mechanistic interpretability (i.e., the systematic study of how neural networks…

Computation and Language · Computer Science 2026-02-13 Usman Naseem

Machine Learning models from other fields, like Computational Linguistics, have been transplanted to Software Engineering tasks, often quite successfully. Yet a transplanted model's initial success at a given task does not necessarily mean…

Software Engineering · Computer Science 2020-09-02 Yangruibo Ding , Baishakhi Ray , Premkumar Devanbu , Vincent J. Hellendoorn

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

Test-time interventions for language models can enhance factual accuracy, mitigate harmful outputs, and improve model efficiency without costly retraining. But despite a flood of new methods, different types of interventions are largely…

Recent breakthroughs in NLP research, such as the advent of Transformer models have indisputably contributed to major advancements in several tasks. However, few works research robustness and explainability issues of their evaluation…

Computation and Language · Computer Science 2022-10-31 Maria Lymperaiou , George Manoliadis , Orfeas Menis Mastromichalakis , Edmund G. Dervakos , Giorgos Stamou

Deep learning methods have become very popular for the processing of natural images, and were then successfully adapted to the neuroimaging field. As these methods are non-transparent, interpretability methods are needed to validate them…

Computer Vision and Pattern Recognition · Computer Science 2022-04-15 Elina Thibeau-Sutre , Sasha Collin , Ninon Burgos , Olivier Colliot

Mechanistic interpretability often uses activation patching, causal tracing, path patching, and steering directions to reveal behaviorally meaningful directions in Transformer activation space. This paper develops a field-theoretic…

Machine Learning · Computer Science 2026-05-26 David N. Olivieri , Antonio F. Pérez Rodríguez

Recent works have proposed that activations in language models can be modelled as sparse linear combinations of vectors corresponding to features of input text. Under this assumption, these works aimed to reconstruct feature directions…

Machine Learning · Computer Science 2023-10-17 Mingyang Deng , Lucas Tao , Joe Benton

Mechanistic interpretability aims to understand how neural networks generalize beyond their training data by reverse-engineering their internal structures. We introduce patterning as the dual problem: given a desired form of generalization,…

Machine Learning · Computer Science 2026-01-21 George Wang , Daniel Murfet

Neural networks are growing more capable on their own, but we do not understand their neural mechanisms. Understanding these mechanisms' decision-making processes, or mechanistic interpretability, enables (1) accountability and control in…

Computation and Language · Computer Science 2026-03-02 Mason Kadem , Rong Zheng

Mechanistic interpretability aims to understand the computational mechanisms underlying neural networks' capabilities in order to accomplish concrete scientific and engineering goals. Progress in this field thus promises to provide greater…

The emergence of large-scale pretrained language models has posed unprecedented challenges in deriving explanations of why the model has made some predictions. Stemmed from the compositional nature of languages, spurious correlations have…

Computation and Language · Computer Science 2023-05-04 Ruochen Zhao , Shafiq Joty , Yongjie Wang , Tan Wang

Neural Machine Translation (NMT) models have shown remarkable performance but remain largely opaque in their decision making processes. The interpretability of these models, especially their internal attention mechanisms, is critical for…

Artificial Intelligence · Computer Science 2024-12-30 Anurag Mishra