Search Results for author:
Found 49 papers, 11 papers with code
The RealHumanEval: Evaluating Large Language Models' Abilities to Support Programmers
Evaluation of large language models (LLMs) for code has primarily relied on static benchmarks, including HumanEval (Chen et al., 2021), which measure the ability of LLMs to generate complete code that passes unit tests.
Multi-Level Explanations for Generative Language Models
To address the challenges of text as output and long text inputs, we propose a general framework called MExGen that can be instantiated with different attribution algorithms.
Detectors for Safe and Reliable LLMs: Implementations, Uses, and Limitations
Large language models (LLMs) are susceptible to a variety of risks, from non-faithful output to biased and toxic generations.
Causal Bandits with General Causal Models and Interventions
First, the structural causal models (SCMs) are assumed to be unknown and drawn arbitrarily from a general class $\mathcal{F}$ of Lipschitz-continuous functions.
Trust Regions for Explanations via Black-Box Probabilistic Certification
fidelity, stability), can we find the largest hypercube (i. e., $\ell_{\infty}$ ball) centered at the example such that when the explanation is applied to all examples within the hypercube, (with high probability) a quality criterion is met (viz.
Effective Human-AI Teams via Learned Natural Language Rules and Onboarding
In this work, we propose to learn rules, grounded in data regions and described in natural language, that illustrate how the human should collaborate with the AI.
SalUn: Empowering Machine Unlearning via Gradient-based Weight Saliency in Both Image Classification and Generation
To address these challenges, we introduce the concept of 'weight saliency' for MU, drawing parallels with input saliency in model explanation.
Interpretable Differencing of Machine Learning Models
Understanding the differences between machine learning (ML) models is of interest in scenarios ranging from choosing amongst a set of competing models, to updating a deployed model with new training data.
Convex Bounds on the Softmax Function with Applications to Robustness Verification
The softmax function is a ubiquitous component at the output of neural networks and increasingly in intermediate layers as well.
Who Should Predict? Exact Algorithms For Learning to Defer to Humans
We show that prior approaches can fail to find a human-AI system with low misclassification error even when there exists a linear classifier and rejector that have zero error (the realizable setting).
On the Safety of Interpretable Machine Learning: A Maximum Deviation Approach
Interpretable and explainable machine learning has seen a recent surge of interest.
Downstream Fairness Caveats with Synthetic Healthcare Data
In this paper, we evaluate the fairness of models generated on two healthcare datasets for gender and race biases.
Analogies and Feature Attributions for Model Agnostic Explanation of Similarity Learners
We first propose a method that provides feature attributions to explain the similarity between a pair of inputs as determined by a black box similarity learner.
FROTE: Feedback Rule-Driven Oversampling for Editing Models
However, in such scenarios, it may take time for sufficient training data to accumulate in order to retrain the model to reflect the new decision boundaries.
Ground-Truth, Whose Truth? -- Examining the Challenges with Annotating Toxic Text Datasets
The use of machine learning (ML)-based language models (LMs) to monitor content online is on the rise.
CoFrNets: Interpretable Neural Architecture Inspired by Continued Fractions
We experiment on nonlinear synthetic functions and are able to accurately model as well as estimate feature attributions and even higher order terms in some cases, which is a testament to the representational power as well as interpretability of such architectures.
Interpretable and Fair Boolean Rule Sets via Column Generation
This paper considers the learning of Boolean rules in disjunctive normal form (DNF, OR-of-ANDs, equivalent to decision rule sets) as an interpretable model for classification.
AI Explainability 360: Impact and Design
As artificial intelligence and machine learning algorithms become increasingly prevalent in society, multiple stakeholders are calling for these algorithms to provide explanations.
Your fairness may vary: Pretrained language model fairness in toxic text classification
Through the analysis of more than a dozen pretrained language models of varying sizes on two toxic text classification tasks (English), we demonstrate that focusing on accuracy measures alone can lead to models with wide variation in fairness characteristics.
Treatment Effect Estimation using Invariant Risk Minimization
Inferring causal individual treatment effect (ITE) from observational data is a challenging problem whose difficulty is exacerbated by the presence of treatment assignment bias.
Optimal Policies for the Homogeneous Selective Labels Problem
Selective labels are a common feature of consequential decision-making applications, referring to the lack of observed outcomes under one of the possible decisions.
DAGs with No Fears: A Closer Look at Continuous Optimization for Learning Bayesian Networks
This paper re-examines a continuous optimization framework dubbed NOTEARS for learning Bayesian networks.
Deciding Fast and Slow: The Role of Cognitive Biases in AI-assisted Decision-making
We, then, conduct a second user experiment which shows that our time allocation strategy with explanation can effectively de-anchor the human and improve collaborative performance when the AI model has low confidence and is incorrect.
Consumer-Driven Explanations for Machine Learning Decisions: An Empirical Study of Robustness
Many proposed methods for explaining machine learning predictions are in fact challenging to understand for nontechnical consumers.
Is There a Trade-Off Between Fairness and Accuracy? A Perspective Using Mismatched Hypothesis Testing
Moreover, the same classifier yields the lack of a trade-off with respect to ideal distributions while yielding a trade-off when accuracy is measured with respect to the given (possibly biased) dataset.
One Explanation Does Not Fit All: A Toolkit and Taxonomy of AI Explainability Techniques
Equally important, we provide a taxonomy to help entities requiring explanations to navigate the space of explanation methods, not only those in the toolkit but also in the broader literature on explainability.
Characterization of Overlap in Observational Studies
Overlap between treatment groups is required for non-parametric estimation of causal effects.
Teaching AI to Explain its Decisions Using Embeddings and Multi-Task Learning
Using machine learning in high-stakes applications often requires predictions to be accompanied by explanations comprehensible to the domain user, who has ultimate responsibility for decisions and outcomes.
Generalized Linear Rule Models
Column generation is used to optimize over an exponentially large space of rules without pre-generating a large subset of candidates or greedily boosting rules one by one.
Optimized Score Transformation for Consistent Fair Classification
We derive a closed-form expression for the optimal transformed scores and a convex optimization problem for the transformation parameters.
Interpretable Subgroup Discovery in Treatment Effect Estimation with Application to Opioid Prescribing Guidelines
The dearth of prescribing guidelines for physicians is one key driver of the current opioid epidemic in the United States.
TED: Teaching AI to Explain its Decisions
Artificial intelligence systems are being increasingly deployed due to their potential to increase the efficiency, scale, consistency, fairness, and accuracy of decisions.
Parallel Bayesian Network Structure Learning
Recent advances in Bayesian Network (BN) structure learning have focused on local-to-global learning, where the graph structure is learned via one local subgraph at a time.
Teaching Meaningful Explanations
The adoption of machine learning in high-stakes applications such as healthcare and law has lagged in part because predictions are not accompanied by explanations comprehensible to the domain user, who often holds the ultimate responsibility for decisions and outcomes.
Boolean Decision Rules via Column Generation
This paper considers the learning of Boolean rules in either disjunctive normal form (DNF, OR-of-ANDs, equivalent to decision rule sets) or conjunctive normal form (CNF, AND-of-ORs) as an interpretable model for classification.
On the Supermodularity of Active Graph-based Semi-supervised Learning with Stieltjes Matrix Regularization
Active graph-based semi-supervised learning (AG-SSL) aims to select a small set of labeled examples and utilize their graph-based relation to other unlabeled examples to aid in machine learning tasks.
Optimized Pre-Processing for Discrimination Prevention
Non-discrimination is a recognized objective in algorithmic decision making.
Distribution-Preserving k-Anonymity
Preserving the privacy of individuals by protecting their sensitive attributes is an important consideration during microdata release.
Optimized Data Pre-Processing for Discrimination Prevention
Non-discrimination is a recognized objective in algorithmic decision making.
A Constant-Factor Bi-Criteria Approximation Guarantee for k-means++
This paper studies the $k$-means++ algorithm for clustering as well as the class of $D^\ell$ sampling algorithms to which $k$-means++ belongs.
Interpretable Two-level Boolean Rule Learning for Classification
As a contribution to interpretable machine learning research, we develop a novel optimization framework for learning accurate and sparse two-level Boolean rules.
A Constant-Factor Bi-Criteria Approximation Guarantee for $k$-means++
This paper studies the $k$-means++ algorithm for clustering as well as the class of $D^\ell$ sampling algorithms to which $k$-means++ belongs.
Interpretable Two-level Boolean Rule Learning for Classification
Experiments show that the two-level rules can yield noticeably better performance than one-level rules due to their dramatically larger modeling capacity, and the two algorithms based on the Hamming distance formulation are generally superior to the other two-level rule learning methods in our comparison.
Statistical Estimation and Clustering of Group-invariant Orientation Parameters
We treat the problem of estimation of orientation parameters whose values are invariant to transformations from a spherical symmetry group.
A Dictionary Approach to EBSD Indexing
We discretize the domain of the forward model onto a dense grid of Euler angles and for each measured pattern we identify the most similar patterns in the dictionary.
Coercive Region-level Registration for Multi-modal Images
We propose a coercive approach to simultaneously register and segment multi-modal images which share similar spatial structure.
Parameter estimation in spherical symmetry groups
This paper considers statistical estimation problems where the probability distribution of the observed random variable is invariant with respect to actions of a finite topological group.
Spectral Correlation Hub Screening of Multivariate Time Series
This property permits independent correlation analysis at each frequency, alleviating the computational and statistical challenges of high-dimensional time series.
Marginal Likelihoods for Distributed Parameter Estimation of Gaussian Graphical Models
In this paper, we propose a general framework for distributed estimation based on a maximum marginal likelihood (MML) approach.
