English
Related papers

Related papers: The Neglected Baseline in Model Interpretation

200 papers

State of the art machine learning algorithms are highly optimized to provide the optimal prediction possible, naturally resulting in complex models. While these models often outperform simpler more interpretable models by order of…

Machine Learning · Statistics 2016-11-24 Yotam Hechtlinger

Deep learning has achieved remarkable success across many domains, but it has also created a growing demand for interpretability in model predictions. Although many explainable machine learning methods have been proposed, post-hoc…

Machine Learning · Computer Science 2026-01-28 Shijian Xu , Marcello Massimo Negri , Volker Roth

Interpretability is an important area of research for safe deployment of machine learning systems. One particular type of interpretability method attributes model decisions to input features. Despite active development, quantitative…

Machine Learning · Computer Science 2019-11-06 Mengjiao Yang , Been Kim

Attribution methods aim to explain a neural network's prediction by highlighting the most relevant image areas. A popular approach is to backpropagate (BP) a custom relevance score using modified rules, rather than the gradient. We analyze…

Machine Learning · Computer Science 2024-02-20 Leon Sixt , Maximilian Granz , Tim Landgraf

Model interpretation is essential in data mining and knowledge discovery. It can help understand the intrinsic model working mechanism and check if the model has undesired characteristics. A popular way of performing model interpretation is…

Machine Learning · Statistics 2020-08-04 Jian Liang , Bing Bai , Yuren Cao , Kun Bai , Fei Wang

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

Scaling inference compute in large language models (LLMs) through repeated sampling consistently increases the coverage (fraction of problems solved) as the number of samples increases. We conjecture that this observed improvement is…

Computation and Language · Computer Science 2024-10-22 Gal Yona , Or Honovich , Omer Levy , Roee Aharoni

Gradient-based analysis methods, such as saliency map visualizations and adversarial input perturbations, have found widespread use in interpreting neural NLP models due to their simplicity, flexibility, and most importantly, their…

Computation and Language · Computer Science 2020-10-13 Junlin Wang , Jens Tuyls , Eric Wallace , Sameer Singh

Machine learning models are often deployed in different settings than they were trained and validated on, posing a challenge to practitioners who wish to predict how well the deployed model will perform on a target distribution. If an…

Machine Learning · Computer Science 2022-04-12 Mayee Chen , Karan Goel , Nimit S. Sohoni , Fait Poms , Kayvon Fatahalian , Christopher Ré

As an emerging interpretable technique, Generalized Additive Models (GAMs) adopt neural networks to individually learn non-linear functions for each feature, which are then combined through a linear model for final predictions. Although…

Machine Learning · Computer Science 2024-08-01 Viet Duong , Qiong Wu , Zhengyi Zhou , Hongjue Zhao , Chenxiang Luo , Eric Zavesky , Huaxiu Yao , Huajie Shao

With the recent addition of Retrieval-Augmented Generation (RAG), the scope and importance of Information Retrieval (IR) has expanded. As a result, the importance of a deeper understanding of IR models also increases. However,…

Information Retrieval · Computer Science 2024-07-08 Mathias Vast , Basile Van Cooten , Laure Soulier , Benjamin Piwowarski

Recent advancements have enhanced the capability of Multimodal Large Language Models (MLLMs) to comprehend multi-image information. However, existing benchmarks primarily evaluate answer correctness, overlooking whether models genuinely…

Computer Vision and Pattern Recognition · Computer Science 2025-05-26 Pengfei Wang , Guohai Xu , Weinong Wang , Junjie Yang , Jie Lou , Yunhua Xue

Imitation learning enables agents to reuse and adapt the hard-won expertise of others, offering a solution to several key challenges in learning behavior. Although it is easy to observe behavior in the real-world, the underlying actions may…

Machine Learning · Computer Science 2021-07-09 Andrew Jaegle , Yury Sulsky , Arun Ahuja , Jake Bruce , Rob Fergus , Greg Wayne

We introduce Generalized Integrated Gradients (GIG), a formal extension of the Integrated Gradients (IG) (Sundararajan et al., 2017) method for attributing credit to the input variables of a predictive model. GIG improves IG by explaining a…

Machine Learning · Computer Science 2019-09-10 John Merrill , Geoff Ward , Sean Kamkar , Jay Budzik , Douglas Merrill

Understanding node representations in graph-based models is crucial for uncovering biases ,diagnosing errors, and building trust in model decisions. However, previous work on explainable AI for node representations has primarily emphasized…

Machine Learning · Computer Science 2024-11-04 Ying-Chun Lin , Jennifer Neville , Cassiano Becker , Purvanshi Metha , Nabiha Asghar , Vipul Agarwal

Complex statistical models such as scalar-on-image regression often require strong assumptions to overcome the issue of non-identifiability. While in theory it is well understood that model assumptions can strongly influence the results,…

Methodology · Statistics 2020-05-04 Clara Happ , Sonja Greven , Volker J. Schmid

With the growing pervasiveness of artificial intelligence, the ability to explain the inferences made by machine learning models has become increasingly important. Numerous techniques for model explainability have been proposed, with…

Human-Computer Interaction · Computer Science 2026-04-08 Nicola Rossberg , Bennett Kleinberg , Barry O'Sullivan , Luca Longo , Andrea Visentin

Interpretation of a machine learning induced models is critical for feature engineering, debugging, and, arguably, compliance. Yet, best of breed machine learning models tend to be very complex. This paper presents a method for model…

Machine Learning · Computer Science 2018-02-27 Noa Avigdor-Elgrabli , Alex Libov , Michael Viderman , Ran Wolff

Two popular approaches for relating correlated measurements of a non-Gaussian response variable to a set of predictors are to fit a marginal model using generalized estimating equations and to fit a generalized linear mixed model by…

Methodology · Statistics 2017-02-23 Jeffrey J. Gory , Peter F. Craigmile , Steven N. MacEachern

While interpretability methods identify a model's learned concepts, they overlook the relationships between concepts that make up its abstractions and inform its ability to generalize to new data. To assess whether models' have learned…

Machine Learning · Computer Science 2025-11-04 Angie Boggust , Hyemin Bang , Hendrik Strobelt , Arvind Satyanarayan