Author name cluster

Sinead Williamson

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

6 papers

1 author row

TMLR Journal 2026 Journal Article

ExpertLens: Activation steering features are highly interpretable

Masha Fedzechkina
Eleonora Gualdoni
Sinead Williamson
Katherine Metcalf
Skyler Seto
Barry-John Theobald

Activation steering methods in large language models (LLMs) have emerged as an effective way to perform targeted updates to enhance generated language without requiring large amounts of adaptation data. We ask whether the features discovered by activation steering methods are interpretable. We identify neurons responsible for specific concepts (e.g., ''cat'') using the ''finding experts'' method from research on activation steering and show that the ExpertLens, i.e., inspection of these neurons, provides insights about model representation. We find that ExpertLens representations are stable across models and datasets and closely align with human representations inferred from behavioral data, matching inter-human alignment levels. ExpertLens significantly outperforms the alignment captured by word/sentence embeddings and sparse autoencoder (SAE) features. By reconstructing human concept organization through ExpertLens, we show that it enables a granular view of LLM concept representation. Our findings suggest that ExpertLens is a flexible and lightweight approach for capturing and analyzing model representations.

PDF Details

IJCAI Conference 2020 Conference Paper

Certifai: A Toolkit for Building Trust in AI Systems

Jette Henderson
Shubham Sharma
Alan Gee
Valeri Alexiev
Steve Draper
Carlos Marin
Yessel Hinojosa
Christine Draper

As more companies and governments build and use machine learning models to automate decisions, there is an ever-growing need to monitor and evaluate these models' behavior once they are deployed. Our team at CognitiveScale has developed a toolkit called Cortex Certifai to answer this need. Cortex Certifai is a framework that assesses aspects of robustness, fairness, and interpretability of any classification or regression model trained on tabular data, without requiring access to its internal workings. Additionally, Cortex Certifai allows users to compare models along these different axes and only requires 1) query access to the model and 2) an “evaluation” dataset. At its foundation, Cortex Certifai generates counterfactual explanations, which are synthetic data points close to input data points but differing in terms of model prediction. The tool then harnesses characteristics of these counterfactual explanations to analyze different aspects of the supplied model and delivers evaluations relevant to a variety of different stakeholders (e. g. , model developers, risk analysts, compliance officers). Cortex Certifai can be configured and executed using a command-line interface (CLI), within jupyter notebooks, or on the cloud, and the results are recorded in JSON files and can be visualized in an interactive console. Using these reports, stakeholders can understand, monitor, and build trust in their AI systems. In this paper, we provide a brief overview of a demonstration of Cortex Certifai's capabilities.

PDF Details DOI

NeurIPS Conference 2016 Conference Paper

Variance Reduction in Stochastic Gradient Langevin Dynamics

Kumar Avinava Dubey
Sashank J. Reddi
Sinead Williamson
Barnabas Poczos
Alexander Smola
Eric Xing

Stochastic gradient-based Monte Carlo methods such as stochastic gradient Langevin dynamics are useful tools for posterior inference on large scale datasets in many machine learning applications. These methods scale to large datasets by using noisy gradients calculated using a mini-batch or subset of the dataset. However, the high variance inherent in these noisy gradients degrades performance and leads to slower mixing. In this paper, we present techniques for reducing variance in stochastic gradient Langevin dynamics, yielding novel stochastic Monte Carlo methods that improve performance by reducing the variance in the stochastic gradient. We show that our proposed method has better theoretical guarantees on convergence rate than stochastic Langevin dynamics. This is complemented by impressive empirical results obtained on a variety of real world datasets, and on four different machine learning tasks (regression, classification, independent component analysis and mixture modeling). These theoretical and empirical contributions combine to make a compelling case for using variance reduction in stochastic Monte Carlo methods.

PDF Details

NeurIPS Conference 2014 Conference Paper

Dependent nonparametric trees for dynamic hierarchical clustering

Kumar Avinava Dubey
Qirong Ho
Sinead Williamson
Eric Xing

Hierarchical clustering methods offer an intuitive and powerful way to model a wide variety of data sets. However, the assumption of a fixed hierarchy is often overly restrictive when working with data generated over a period of time: We expect both the structure of our hierarchy, and the parameters of the clusters, to evolve with time. In this paper, we present a distribution over collections of time-dependent, infinite-dimensional trees that can be used to model evolving hierarchies, and present an efficient and scalable algorithm for performing approximate inference in such a model. We demonstrate the efficacy of our model and inference algorithm on both synthetic data and real-world document corpora.

PDF Details

NeurIPS Conference 2013 Conference Paper

Restricting exchangeable nonparametric distributions

Sinead Williamson
Steve MacEachern
Eric Xing

Distributions over exchangeable matrices with infinitely many columns are useful in constructing nonparametric latent variable models. However, the distribution implied by such models over the number of features exhibited by each data point may be poorly-suited for many modeling tasks. In this paper, we propose a class of exchangeable nonparametric priors obtained by restricting the domain of existing models. Such models allow us to specify the distribution over the number of features per data point, and can achieve better performance on data sets where the number of features is not well-modeled by the original distribution.

PDF Details

NeurIPS Conference 2012 Conference Paper

Slice sampling normalized kernel-weighted completely random measure mixture models

Nick Foti
Sinead Williamson

A number of dependent nonparametric processes have been proposed to model non-stationary data with unknown latent dimensionality. However, the inference algorithms are often slow and unwieldy, and are in general highly specific to a given model formulation. In this paper, we describe a wide class of nonparametric processes, including several existing models, and present a slice sampler that allows efficient inference across this class of models.

PDF Details