Search Results for author:
Found 35 papers, 14 papers with code
Final-Model-Only Data Attribution with a Unifying View of Gradient-Based Methods
To serve as a gold standard for TDA in this "final-model-only" setting, we propose further training, with appropriate adjustment and averaging, to measure the sensitivity of the given model to training instances.
When in Doubt, Cascade: Towards Building Efficient and Capable Guardrails
Motivated by findings from developing a detector for social bias, we adopt the notion of a use-mention distinction - which we identified as the primary source of under-performance in the preliminary versions of our social bias detector.
Large Language Model Confidence Estimation via Black-Box Access
Estimating uncertainty or confidence in the responses of a model can be significant in evaluating trust not only in the responses, but also in the model as a whole.
$\textit{Trans-LoRA}$: towards data-free Transferable Parameter Efficient Finetuning
Our approach relies on synthetic data to transfer LoRA modules.
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.
Thermometer: Towards Universal Calibration for Large Language Models
Addressing these challenges, we propose THERMOMETER, a calibration approach tailored to LLMs.
Are Uncertainty Quantification Capabilities of Evidential Deep Learning a Mirage?
This paper questions the effectiveness of a modern predictive uncertainty quantification approach, called \emph{evidential deep learning} (EDL), in which a single neural network model is trained to learn a meta distribution over the predictive distribution by minimizing a specific objective function.
Assessment of Prediction Intervals Using Uncertainty Characteristics Curves
Accurate quantification of model uncertainty has long been recognized as a fundamental requirement for trusted AI.
Reliable Gradient-free and Likelihood-free Prompt Tuning
Due to privacy or commercial constraints, large pre-trained language models (PLMs) are often offered as black-box APIs.
Post-hoc Uncertainty Learning using a Dirichlet Meta-Model
It is known that neural networks have the problem of being over-confident when directly using the output label distribution to generate uncertainty measures.
Fair Infinitesimal Jackknife: Mitigating the Influence of Biased Training Data Points Without Refitting
The dropping of training points is done in principle, but in practice does not require the model to be refit.
Are you using test log-likelihood correctly?
Test log-likelihood is commonly used to compare different models of the same data or different approximate inference algorithms for fitting the same probabilistic model.
Post-hoc loss-calibration for Bayesian neural networks
Bayesian decision theory provides an elegant framework for acting optimally under uncertainty when tractable posterior distributions are available.
Measuring the robustness of Gaussian processes to kernel choice
We demonstrate in both synthetic and real-world examples that decisions made with a GP can exhibit non-robustness to kernel choice, even when prior draws are qualitatively interchangeable to a user.
Uncertainty Quantification 360: A Holistic Toolkit for Quantifying and Communicating the Uncertainty of AI
In this paper, we describe an open source Python toolkit named Uncertainty Quantification 360 (UQ360) for the uncertainty quantification of AI models.
Uncertainty Characteristics Curves: A Systematic Assessment of Prediction Intervals
Accurate quantification of model uncertainty has long been recognized as a fundamental requirement for trusted AI.
EVA: Generating Longitudinal Electronic Health Records Using Conditional Variational Autoencoders
De-identified EHRs do not adequately address the needs of health systems, as de-identified data are susceptible to re-identification and its volume is also limited.
Model Fusion with Kullback--Leibler Divergence
Our algorithm relies on a mean field assumption for both the fused model and the individual dataset posteriors and proceeds using a simple assign-and-average approach.
Approximate Cross-Validation for Structured Models
But this existing ACV work is restricted to simpler models by the assumptions that (i) data across CV folds are independent and (ii) an exact initial model fit is available.
Statistical Model Aggregation via Parameter Matching
We consider the problem of aggregating models learned from sequestered, possibly heterogeneous datasets.
Isolating Latent Structure with Cross-population Variational Autoencoders
A significant body of recent work has examined variational autoencoders as a powerful approach for tasks which involve modeling the distribution of complex data such as images and text.
Quality of Uncertainty Quantification for Bayesian Neural Network Inference
Bayesian Neural Networks (BNNs) place priors over the parameters in a neural network.
Bayesian Nonparametric Federated Learning of Neural Networks
In federated learning problems, data is scattered across different servers and exchanging or pooling it is often impractical or prohibited.
Probabilistic Federated Neural Matching
In federated learning problems, data is scattered across different servers and exchanging or pooling it is often impractical or prohibited.
DPVis: Visual Analytics with Hidden Markov Models for Disease Progression Pathways
Clinical researchers use disease progression models to understand patient status and characterize progression patterns from longitudinal health records.
Projected BNNs: Avoiding weight-space pathologies by learning latent representations of neural network weights
As machine learning systems get widely adopted for high-stake decisions, quantifying uncertainty over predictions becomes crucial.
Unsupervised learning with contrastive latent variable models
Here, we present a probabilistic model for dimensionality reduction to discover signal that is enriched in the target dataset relative to the background dataset.
Structured Variational Learning of Bayesian Neural Networks with Horseshoe Priors
Bayesian Neural Networks (BNNs) have recently received increasing attention for their ability to provide well-calibrated posterior uncertainties.
Simultaneous Modeling of Multiple Complications for Risk Profiling in Diabetes Care
The proposed method is favorable for healthcare applications because in additional to improved prediction performance, relationships among the different risks and risk factors are also identified.
Personalizing Gesture Recognition Using Hierarchical Bayesian Neural Networks
Leveraging recent work on learning Bayesian neural networks, we build fast, scalable algorithms for inferring the posterior distribution over all network weights in the hierarchy.
Model Selection in Bayesian Neural Networks via Horseshoe Priors
Bayesian Neural Networks (BNNs) have recently received increasing attention for their ability to provide well-calibrated posterior uncertainties.
From Deformations to Parts: Motion-based Segmentation of 3D Objects
We develop a method for discovering the parts of an articulated object from aligned meshes capturing various three-dimensional (3D) poses.
Spatial distance dependent Chinese restaurant processes for image segmentation
The distance dependent Chinese restaurant process (ddCRP) was recently introduced to accommodate random partitions of non-exchangeable data.
