7.6k citations · 11.1k across the 23 of their papers we have counts for
23 papers
Sparks of Artificial General Intelligence: Early experiments with GPT-4
Sébastien Bubeck, Varun Chandrasekaran, Ronen Eldan +11
Artificial intelligence (AI) researchers have been developing and refining large language models (LLMs) that exhibit remarkable capabilities across a variety of domains and tasks,…
ART: Automatic multi-step reasoning and tool-use for large language models
Bhargavi Paranjape, Scott Lundberg, Sameer Singh +3
Large language models (LLMs) can perform complex reasoning in few- and zero-shot settings by generating intermediate chain of thought (CoT) reasoning steps. Further, each reasoning…
Adaptive Testing of Computer Vision Models
Irena Gao, Gabriel Ilharco, Scott Lundberg +1
Vision models often fail systematically on groups of data that share common semantic characteristics (e.g., rare objects or unusual scenes), but identifying these failure modes is…
Fixing Model Bugs with Natural Language Patches
Shikhar Murty, Christopher D. Manning, Scott Lundberg +1
Current approaches for fixing systematic problems in NLP models (e.g. regex patches, finetuning on more data) are either brittle, or labor-intensive and liable to shortcuts. In con…
Algorithms to estimate Shapley value feature attributions
Hugh Chen, Ian C. Covert, Scott M. Lundberg +1
Feature attributions based on the Shapley value are popular for explaining machine learning models; however, their estimation is complex from both a theoretical and computational s…
Explaining a Series of Models by Propagating Shapley Values
Hugh Chen, Scott M. Lundberg, Su-In Lee
Local feature attribution methods are increasingly used to explain complex machine learning models. However, current methods are limited because they are extremely expensive to com…
Axiomatic Explanations for Visual Search, Retrieval, and Similarity Learning
Mark Hamilton, Scott Lundberg, Lei Zhang +2
Visual search, recommendation, and contrastive similarity learning power technologies that impact billions of users worldwide. Modern model architectures can be complex and difficu…
Explaining by Removing: A Unified Framework for Model Explanation
Ian Covert, Scott Lundberg, Su-In Lee
Researchers have proposed a wide variety of model explanation approaches, but it remains unclear how most methods are related or when one method is preferable to another. We descri…
Feature Removal Is a Unifying Principle for Model Explanation Methods
Ian Covert, Scott Lundberg, Su-In Lee
Researchers have proposed a wide variety of model explanation approaches, but it remains unclear how most methods are related or when one method is preferable to another. We examin…
Shapley Flow: A Graph-based Approach to Interpreting Model Predictions
Jiaxuan Wang, Jenna Wiens, Scott Lundberg
Many existing approaches for estimating feature importance are problematic because they ignore or hide dependencies among features. A causal graph, which encodes the relationships…
True to the Model or True to the Data?
Hugh Chen, Joseph D. Janizek, Scott Lundberg +1
A variety of recent papers discuss the application of Shapley values, a concept for explaining coalitional games, for feature attribution in machine learning. However, the correct…
Understanding Global Feature Contributions With Additive Importance Measures
Ian Covert, Scott Lundberg, Su-In Lee
Understanding the inner workings of complex machine learning models is a long-standing problem and most recent research has focused on local interpretability. To assess the role of…
Forecasting adverse surgical events using self-supervised transfer learning for physiological signals
Hugh Chen, Scott Lundberg, Gabe Erion +2
Hundreds of millions of surgical procedures take place annually across the world, which generate a prevalent type of electronic health record (EHR) data comprising time series phys…
Explaining Models by Propagating Shapley Values of Local Components
Hugh Chen, Scott Lundberg, Su-In Lee
In healthcare, making the best possible predictions with complex models (e.g., neural networks, ensembles/stacks of different models) can impact patient welfare. In order to make t…
Improving performance of deep learning models with axiomatic attribution priors and expected gradients
Gabriel Erion, Joseph D. Janizek, Pascal Sturmfels +2
Recent research has demonstrated that feature attribution methods for deep networks can themselves be incorporated into training; these attribution priors optimize for a model whos…
Explainable AI for Trees: From Local Explanations to Global Understanding
Scott M. Lundberg, Gabriel Erion, Hugh Chen +7
Tree-based machine learning models such as random forests, decision trees, and gradient boosted trees are the most popular non-linear predictive models used in practice today, yet…
Consistent Individualized Feature Attribution for Tree Ensembles
Scott M. Lundberg, Gabriel G. Erion, Su-In Lee
Interpreting predictions from tree ensemble methods such as gradient boosting machines and random forests is important, yet feature attribution for trees is often heuristic and not…
Hybrid Gradient Boosting Trees and Neural Networks for Forecasting Operating Room Data
Hugh Chen, Scott Lundberg, Su-In Lee
Time series data constitutes a distinct and growing problem in machine learning. As the corpus of time series data grows larger, deep models that simultaneously learn features and…
Anesthesiologist-level forecasting of hypoxemia with only SpO2 data using deep learning
Gabriel Erion, Hugh Chen, Scott M. Lundberg +1
We use a deep learning model trained only on a patient's blood oxygenation data (measurable with an inexpensive fingertip sensor) to predict impending hypoxemia (low blood oxygen)…
Checkpoint Ensembles: Ensemble Methods from a Single Training Process
Hugh Chen, Scott Lundberg, Su-In Lee
We present the checkpoint ensembles method that can learn ensemble models on a single training process. Although checkpoint ensembles can be applied to any parametric iterative lea…
Consistent feature attribution for tree ensembles
Scott M. Lundberg, Su-In Lee
Note that a newer expanded version of this paper is now available at: arXiv:1802.03888 It is critical in many applications to understand what features are important for a model, an…
A Unified Approach to Interpreting Model Predictions
Scott Lundberg, Su-In Lee
Understanding why a model makes a certain prediction can be as crucial as the prediction's accuracy in many applications. However, the highest accuracy for large modern datasets is…
An unexpected unity among methods for interpreting model predictions
Scott Lundberg, Su-In Lee
Understanding why a model made a certain prediction is crucial in many data science fields. Interpretable predictions engender appropriate trust and provide insight into how the mo…