arXiv subjects

Helen Zhou

Publications and source records attributed to Helen Zhou.

17 recordsLinked to original sources

arXiv2026

Improving Methodologies for Agentic Evaluations Across Domains: Leakage of Sensitive Information, Fraud and Cybersecurity Threats

The rapid rise of autonomous AI systems and advancements in agent capabilities are introducing new risks due to reduced oversight of real-world interactions. Yet agent testing remains nascent and is still a developing science. As AI agents begin to be deployed globally, it is important that they handle different languages and cultures accurately and securely. To address this, participants from The International Network for Advanced AI Measurement, Evaluation and Science, including representatives from Singapore, Japan, Australia, Canada, the European Commission, France, Kenya, South Korea, and the United Kingdom have come together to align approaches to agentic evaluations. This is the third exercise, building on insights from two earlier joint testing exercises conducted by the Network in November 2024 and February 2025. The objective is to further refine best practices for testing advanced AI systems. The exercise was split into two strands: (1) common risks, including leakage of sensitive information and fraud, led by Singapore AISI; and (2) cybersecurity, led by UK AISI. A mix of open and closed-weight models were evaluated against tasks from various public agentic benchmarks. Given the nascency of agentic testing, our primary focus was on understanding methodological issues in conducting such tests, rather than examining test results or model capabilities. This collaboration marks an important step forward as participants work together to advance the science of agentic evaluations.

cs.AI↗

arXiv2025

Exploring undercurrents of learning tensions in an LLM-enhanced landscape: A student-centered qualitative perspective on LLM vs Search

Large language models (LLMs) are transforming how students learn by providing readily available tools that can quickly augment or complete various learning activities with non-trivial performance. Similar paradigm shifts have occurred in the past with the introduction of search engines and Wikipedia, which replaced or supplemented traditional information sources such as libraries and books. This study investigates the potential for LLMs to represent the next shift in learning, focusing on their role in information discovery and synthesis compared to existing technologies, such as search engines. Using a within-subjects, counterbalanced design, participants learned new topics using a search engine (Google) and an LLM (ChatGPT). Post-task follow-up interviews explored students' reflections, preferences, pain points, and overall perceptions. We present analysis of their responses that show nuanced insights into when, why, and how students prefer LLMs over search engines, offering implications for educators, policymakers, and technology developers navigating the evolving educational landscape.

cs.HC↗

arXiv2025

Machine Learning for Health symposium 2024 -- Findings track

A collection of the accepted Findings papers that were presented at the 4th Machine Learning for Health symposium (ML4H 2024), which was held on December 15-16, 2024, in Vancouver, BC, Canada. ML4H 2024 invited high-quality submissions describing innovative research in a variety of health-related disciplines including healthcare, biomedicine, and public health. Works could be submitted to either the archival Proceedings track, or the non-archival Findings track. The Proceedings track targeted mature, cohesive works with technical sophistication and high-impact relevance to health. The Findings track promoted works that would spark new insights, collaborations, and discussions at ML4H. Both tracks were given the opportunity to share their work through the in-person poster session. All the manuscripts submitted to ML4H Symposium underwent a double-blind peer-review process.

cs.LG↗

arXiv2024

Learning to Route LLMs with Confidence Tokens

Large language models (LLMs) have demonstrated impressive performance on several tasks and are increasingly deployed in real-world applications. However, especially in high-stakes settings, it becomes vital to know when the output of an LLM may be unreliable. Depending on whether an answer is trustworthy, a system can then choose to route the question to another expert, or otherwise fall back on a safe default behavior. In this work, we study the extent to which LLMs can reliably indicate confidence in their answers, and how this notion of confidence can translate into downstream accuracy gains. We propose Self-Reflection with Error-based Feedback (Self-REF), a lightweight training strategy to teach LLMs to express confidence in whether their answers are correct in a reliable manner. Self-REF introduces confidence tokens into the LLM, from which a confidence score can be extracted. Compared to conventional approaches such as verbalizing confidence and examining token probabilities, we demonstrate empirically that confidence tokens show significant improvements in downstream routing and rejection learning tasks.

cs.CL↗

arXiv2024

Recent Advances, Applications, and Open Challenges in Machine Learning for Health: Reflections from Research Roundtables at ML4H 2023 Symposium

The third ML4H symposium was held in person on December 10, 2023, in New Orleans, Louisiana, USA. The symposium included research roundtable sessions to foster discussions between participants and senior researchers on timely and relevant topics for the \ac{ML4H} community. Encouraged by the successful virtual roundtables in the previous year, we organized eleven in-person roundtables and four virtual roundtables at ML4H 2022. The organization of the research roundtables at the conference involved 17 Senior Chairs and 19 Junior Chairs across 11 tables. Each roundtable session included invited senior chairs (with substantial experience in the field), junior chairs (responsible for facilitating the discussion), and attendees from diverse backgrounds with interest in the session's topic. Herein we detail the organization process and compile takeaways from these roundtable discussions, including recent advances, applications, and open challenges for each topic. We conclude with a summary and lessons learned across all roundtables. This document serves as a comprehensive review paper, summarizing the recent advancements in machine learning for healthcare as contributed by foremost researchers in the field.

cs.LG↗

arXiv2024

REACT: Two Datasets for Analyzing Both Human Reactions and Evaluative Feedback to Robots Over Time

Recent work in Human-Robot Interaction (HRI) has shown that robots can leverage implicit communicative signals from users to understand how they are being perceived during interactions. For example, these signals can be gaze patterns, facial expressions, or body motions that reflect internal human states. To facilitate future research in this direction, we contribute the REACT database, a collection of two datasets of human-robot interactions that display users' natural reactions to robots during a collaborative game and a photography scenario. Further, we analyze the datasets to show that interaction history is an important factor that can influence human reactions to robots. As a result, we believe that future models for interpreting implicit feedback in HRI should explicitly account for this history. REACT opens up doors to this possibility in the future.

cs.RO↗

arXiv2023

MoCo-Transfer: Investigating out-of-distribution contrastive learning for limited-data domains

Medical imaging data is often siloed within hospitals, limiting the amount of data available for specialized model development. With limited in-domain data, one might hope to leverage larger datasets from related domains. In this paper, we analyze the benefit of transferring self-supervised contrastive representations from moment contrast (MoCo) pretraining on out-of-distribution data to settings with limited data. We consider two X-ray datasets which image different parts of the body, and compare transferring from each other to transferring from ImageNet. We find that depending on quantity of labeled and unlabeled data, contrastive pretraining on larger out-of-distribution datasets can perform nearly as well or better than MoCo pretraining in-domain, and pretraining on related domains leads to higher performance than if one were to use the ImageNet pretrained weights. Finally, we provide a preliminary way of quantifying similarity between datasets.

cs.CV↗

arXiv2023

Business Metric-Aware Forecasting for Inventory Management

Time-series forecasts play a critical role in business planning. However, forecasters typically optimize objectives that are agnostic to downstream business goals and thus can produce forecasts misaligned with business preferences. In this work, we demonstrate that optimization of conventional forecasting metrics can often lead to sub-optimal downstream business performance. Focusing on the inventory management setting, we derive an efficient procedure for computing and optimizing proxies of common downstream business metrics in an end-to-end differentiable manner. We explore a wide range of plausible cost trade-off scenarios, and empirically demonstrate that end-to-end optimization often outperforms optimization of standard business-agnostic forecasting metrics (by up to 45.7% for a simple scaling model, and up to 54.0% for an LSTM encoder-decoder model). Finally, we discuss how our findings could benefit other business contexts.

cs.LG↗

arXiv2023

Evaluating Model Performance in Medical Datasets Over Time

Machine learning (ML) models deployed in healthcare systems must face data drawn from continually evolving environments. However, researchers proposing such models typically evaluate them in a time-agnostic manner, splitting datasets according to patients sampled randomly throughout the entire study time period. This work proposes the Evaluation on Medical Datasets Over Time (EMDOT) framework, which evaluates the performance of a model class across time. Inspired by the concept of backtesting, EMDOT simulates possible training procedures that practitioners might have been able to execute at each point in time and evaluates the resulting models on all future time points. Evaluating both linear and more complex models on six distinct medical data sources (tabular and imaging), we show how depending on the dataset, using all historical data may be ideal in many cases, whereas using a window of the most recent data could be advantageous in others. In datasets where models suffer from sudden degradations in performance, we investigate plausible explanations for these shocks. We release the EMDOT package to help facilitate further works in deployment-oriented evaluation over time.

cs.LG↗

arXiv2022

Model Evaluation in Medical Datasets Over Time

Machine learning models deployed in healthcare systems face data drawn from continually evolving environments. However, researchers proposing such models typically evaluate them in a time-agnostic manner, with train and test splits sampling patients throughout the entire study period. We introduce the Evaluation on Medical Datasets Over Time (EMDOT) framework and Python package, which evaluates the performance of a model class over time. Across five medical datasets and a variety of models, we compare two training strategies: (1) using all historical data, and (2) using a window of the most recent data. We note changes in performance over time, and identify possible explanations for these shocks.

cs.LG↗

arXiv2022

Domain Adaptation under Missingness Shift

Rates of missing data often depend on record-keeping policies and thus may change across times and locations, even when the underlying features are comparatively stable. In this paper, we introduce the problem of Domain Adaptation under Missingness Shift (DAMS). Here, (labeled) source data and (unlabeled) target data would be exchangeable but for different missing data mechanisms. We show that if missing data indicators are available, DAMS reduces to covariate shift. Addressing cases where such indicators are absent, we establish the following theoretical results for underreporting completely at random: (i) covariate shift is violated (adaptation is required); (ii) the optimal linear source predictor can perform arbitrarily worse on the target domain than always predicting the mean; (iii) the optimal target predictor can be identified, even when the missingness rates themselves are not; and (iv) for linear models, a simple analytic adjustment yields consistent estimates of the optimal target parameters. In experiments on synthetic and semi-synthetic data, we demonstrate the promise of our methods when assumptions hold. Finally, we discuss a rich family of future extensions.

cs.LG↗

arXiv2022

Learning Clinical Concepts for Predicting Risk of Progression to Severe COVID-19

With COVID-19 now pervasive, identification of high-risk individuals is crucial. Using data from a major healthcare provider in Southwestern Pennsylvania, we develop survival models predicting severe COVID-19 progression. In this endeavor, we face a tradeoff between more accurate models relying on many features and less accurate models relying on a few features aligned with clinician intuition. Complicating matters, many EHR features tend to be under-coded, degrading the accuracy of smaller models. In this study, we develop two sets of high-performance risk scores: (i) an unconstrained model built from all available features; and (ii) a pipeline that learns a small set of clinical concepts before training a risk predictor. Learned concepts boost performance over the corresponding features (C-index 0.858 vs. 0.844) and demonstrate improvements over (i) when evaluated out-of-sample (subsequent time periods). Our models outperform previous works (C-index 0.844-0.872 vs. 0.598-0.810).

cs.LG↗

arXiv2021

Enhanced Twitter Sentiment Classification Using Contextual Information

The rise in popularity and ubiquity of Twitter has made sentiment analysis of tweets an important and well-covered area of research. However, the 140 character limit imposed on tweets makes it hard to use standard linguistic methods for sentiment classification. On the other hand, what tweets lack in structure they make up with sheer volume and rich metadata. This metadata includes geolocation, temporal and author information. We hypothesize that sentiment is dependent on all these contextual factors. Different locations, times and authors have different emotional valences. In this paper, we explored this hypothesis by utilizing distant supervision to collect millions of labelled tweets from different locations, times and authors. We used this data to analyse the variation of tweet sentiments across different authors, times and locations. Once we explored and understood the relationship between these variables and sentiment, we used a Bayesian approach to combine these variables with more standard linguistic features such as n-grams to create a Twitter sentiment classifier. This combined classifier outperforms the purely linguistic classifier, showing that integrating the rich contextual information available on Twitter into sentiment classification is a promising direction of research.

cs.SI↗

arXiv2020

Unpacking the Drop in COVID-19 Case Fatality Rates: A Study of National and Florida Line-Level Data

Since the COVID-19 pandemic first reached the United States, the case fatality rate has fallen precipitously. Several possible explanations have been floated, including greater detection of mild cases due to expanded testing, shifts in age distribution among the infected, lags between confirmed cases and reported deaths, improvements in treatment, mutations in the virus, and decreased viral load as a result of mask-wearing. Using both Florida line-level data and recently released (but incomplete) national line level data from April 1, 2020 to November 1, 2020 on cases, hospitalizations, and deaths--each stratified by age--we unpack the drop in case fatality rate (CFR). Under the hypothesis that improvements in treatment efficacy should correspond to decreases in hospitalization fatality rate (HFR), we find that improvements in the national data do not always match the story told by Florida data. In the national data, treatment improvements between the first wave and the second wave appear substantial, but modest when compared to the drop in aggregate CFR. By contrast, possibly due to constrained resources in a much larger second peak, Florida data suggests comparatively little difference between the first and second wave, with HFR slightly increasing in every age group. However, by November 1st, both Florida and national data suggest significant decreases in age-stratified HFR since April 1st. By accounting for several confounding factors, our analysis shows how age-stratified HFR can provide a more realistic picture of treatment improvements than CFR. One key limitation of our analysis is that the national line-level data remains incomplete and plagued by artifacts. Our analysis highlights the crucial role that this data can play but also the pressing need for public, complete, and high-quality age-stratified line-level data for both cases, hospitalizations, and deaths for all states.

stat.AP↗

arXiv2020

Treatment Policy Learning in Multiobjective Settings with Fully Observed Outcomes

In several medical decision-making problems, such as antibiotic prescription, laboratory testing can provide precise indications for how a patient will respond to different treatment options. This enables us to "fully observe" all potential treatment outcomes, but while present in historical data, these results are infeasible to produce in real-time at the point of the initial treatment decision. Moreover, treatment policies in these settings often need to trade off between multiple competing objectives, such as effectiveness of treatment and harmful side effects. We present, compare, and evaluate three approaches for learning individualized treatment policies in this setting: First, we consider two indirect approaches, which use predictive models of treatment response to construct policies optimal for different trade-offs between objectives. Second, we consider a direct approach that constructs such a set of policies without intermediate models of outcomes. Using a medical dataset of Urinary Tract Infection (UTI) patients, we show that all approaches learn policies that achieve strictly better performance on all outcomes than clinicians, while also trading off between different objectives. We demonstrate additional benefits of the direct approach, including flexibly incorporating other goals such as deferral to physicians on simple cases.

cs.LG↗

arXiv2020

Predicting Mortality Risk in Viral and Unspecified Pneumonia to Assist Clinicians with COVID-19 ECMO Planning

Respiratory complications due to coronavirus disease COVID-19 have claimed tens of thousands of lives in 2020. Many cases of COVID-19 escalate from Severe Acute Respiratory Syndrome (SARS-CoV-2) to viral pneumonia to acute respiratory distress syndrome (ARDS) to death. Extracorporeal membranous oxygenation (ECMO) is a life-sustaining oxygenation and ventilation therapy that may be used for patients with severe ARDS when mechanical ventilation is insufficient to sustain life. While early planning and surgical cannulation for ECMO can increase survival, clinicians report the lack of a risk score hinders these efforts. In this work, we leverage machine learning techniques to develop the PEER score, used to highlight critically ill patients with viral or unspecified pneumonia at high risk of mortality or decompensation in a subpopulation eligible for ECMO. The PEER score is validated on two large, publicly available critical care databases and predicts mortality at least as well as other existing risk scores. Stratifying our cohorts into low-risk and high-risk groups, we find that the high-risk group also has a higher proportion of decompensation indicators such as vasopressor and ventilator use. Finally, the PEER score is provided in the form of a nomogram for direct calculation of patient risk, and can be used to highlight at-risk patients among critical care patients eligible for ECMO.

stat.AP↗

arXiv2016

Digital Stylometry: Linking Profiles Across Social Networks

There is an ever growing number of users with accounts on multiple social media and networking sites. Consequently, there is increasing interest in matching user accounts and profiles across different social networks in order to create aggregate profiles of users. In this paper, we present models for Digital Stylometry, which is a method for matching users through stylometry inspired techniques. We experimented with linguistic, temporal, and combined temporal-linguistic models for matching user accounts, using standard and novel techniques. Using publicly available data, our best model, a combined temporal-linguistic one, was able to correctly match the accounts of 31% of 5,612 distinct users across Twitter and Facebook.

cs.SI↗