English
Related papers

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

200 papers

With the ever-increasing complexity of neural language models, practitioners have turned to methods for understanding the predictions of these models. One of the most well-adopted approaches for model interpretability is feature-based…

Computation and Language · Computer Science 2021-06-10 Muhammad Bilal Zafar , Michele Donini , Dylan Slack , Cédric Archambeau , Sanjiv Das , Krishnaram Kenthapadi

With recent progress on fine-tuning language models around a fixed sparse autoencoder, we disentangle the decoder matrix into almost orthogonal features. This reduces interference and superposition between the features, while keeping…

Machine Learning · Computer Science 2026-02-05 Moritz Miller , Florent Draye , Bernhard Schölkopf

Fine-tuning on generalized tasks such as instruction following, code generation, and mathematics has been shown to enhance language models' performance on a range of tasks. Nevertheless, explanations of how such fine-tuning influences the…

Computation and Language · Computer Science 2024-02-23 Nikhil Prakash , Tamar Rott Shaham , Tal Haklay , Yonatan Belinkov , David Bau

Machine-learning models have demonstrated great success in learning complex patterns that enable them to make predictions about unobserved data. In addition to using models for prediction, the ability to interpret what a model has learned…

Machine Learning · Statistics 2019-11-15 W. James Murdoch , Chandan Singh , Karl Kumbier , Reza Abbasi-Asl , Bin Yu

When predictive models are used to support complex and important decisions, the ability to explain a model's reasoning can increase trust, expose hidden biases, and reduce vulnerability to adversarial attacks. However, attempts at…

Machine Learning · Computer Science 2019-07-11 Dimitris Bertsimas , Arthur Delarue , Patrick Jaillet , Sebastien Martin

The interest in complex deep neural networks for computer vision applications is increasing. This leads to the need for improving the interpretable capabilities of these models. Recent explanation methods present visualizations of the…

Machine Learning · Computer Science 2020-04-24 Dan Valle , Tiago Pimentel , Adriano Veloso

This paper explores the mechanistic interpretability of reinforcement learning (RL) agents through an analysis of a neural network trained on procedural maze environments. By dissecting the network's inner workings, we identified…

Machine Learning · Computer Science 2024-11-05 Tristan Trim , Triston Grayston

Concept-based Models aim to improve interpretability by predicting high-level intermediate concepts, representing a promising approach for deployment in high-risk scenarios. However, they are known to suffer from information leakage,…

Machine Learning · Computer Science 2026-03-25 Enrico Parisini , Tapabrata Chakraborti , Chris Harbron , Ben D. MacArthur , Christopher R. S. Banerji

Trustworthy machine learning is driving a large number of ML community works in order to improve ML acceptance and adoption. The main aspect of trustworthy machine learning are the followings: fairness, uncertainty, robustness,…

Machine Learning · Computer Science 2022-07-08 Gregory Scafarto , Nicolas Posocco , Antoine Bonnefoy

Machine learning has shown successes for complex learning problems in which data/parameters can be multidimensional and too complex for a first-principles based analysis. Some applications that utilize machine learning require human…

Machine Learning · Computer Science 2020-09-14 Nutta Homdee , John Lach

As machine learning becomes an important part of many real world applications affecting human lives, new requirements, besides high predictive accuracy, become important. One important requirement is transparency, which has been associated…

Machine Learning · Computer Science 2019-08-01 Tiago Botari , Rafael Izbicki , Andre C. P. L. F. de Carvalho

The challenge of creating interpretable models has been taken up by two main research communities: ML researchers primarily focused on lower-level explainability methods that suit the needs of engineers, and HCI researchers who have more…

Machine Learning · Computer Science 2024-07-16 Juan D. Pinto , Luc Paquette

Improving neural machine translation (NMT) systems with prompting has achieved significant progress in recent years. In this work, we focus on how to integrate multi-knowledge, multiple types of knowledge, into NMT models to enhance the…

Computation and Language · Computer Science 2023-12-11 Ke Wang , Jun Xie , Yuqi Zhang , Yu Zhao

Probabilistic programming has emerged as a powerful paradigm in statistics, applied science, and machine learning: by decoupling modelling from inference, it promises to allow modellers to directly reason about the processes generating…

Machine Learning · Statistics 2019-06-10 Maria I. Gorinova , Dave Moore , Matthew D. Hoffman

In Reinforcement Learning interpretability generally means to provide insight into the agent's mechanisms such that its decisions are understandable by an expert upon inspection. This definition, with the resulting methods from the…

Artificial Intelligence · Computer Science 2022-03-10 Michele Persiani , Thomas Hellström

Complex machine learning algorithms are used more and more often in critical tasks involving text data, leading to the development of interpretability methods. Among local methods, two families have emerged: those computing importance…

Machine Learning · Computer Science 2025-10-22 Gianluigi Lopardo , Damien Garreau

In meta-learning approaches, it is difficult for a practitioner to make sense of what kind of representations the model employs. Without this ability, it can be difficult to both understand what the model knows as well as to make meaningful…

Machine Learning · Computer Science 2022-04-05 Pedro Sandoval-Segura , Wallace Lawson

We often desire our models to be interpretable as well as accurate. Prior work on optimizing models for interpretability has relied on easy-to-quantify proxies for interpretability, such as sparsity or the number of operations required. In…

Machine Learning · Statistics 2018-11-01 Isaac Lage , Andrew Slavin Ross , Been Kim , Samuel J. Gershman , Finale Doshi-Velez

Explanations for computer vision models are important tools for interpreting how the underlying models work. However, they are often presented in static formats, which pose challenges for users, including information overload, a gap between…

Human-Computer Interaction · Computer Science 2025-04-16 Indu Panigrahi , Sunnie S. Y. Kim , Amna Liaqat , Rohan Jinturkar , Olga Russakovsky , Ruth Fong , Parastoo Abtahi

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