39 citations · 143 across the 29 of their papers we have counts for
33 papers
Self-Preservation in Language Models
Dongkyu Cho, Rumi Chunara, Ali Behrouz
Continual learning (CL) seeks to adapt pretrained models while preserving prior capabilities. Yet the tasks supplied for preservation cover only part of what a model knows, while f…
Continual Learning via Self-Probe Gradients
Dongkyu Cho, Rumi Chunara, Sungmin Cha
Adapting pretrained models to new data can cause catastrophic forgetting of previously learned behavior. When only a few past samples remain, they give continual learning methods s…
Forgetting in Language Models: Capacity, Optimization, and Self-Generated Replay
Martin Marek, Dongkyu Cho, Shikai Qiu +3
Models trained on a new task typically degrade on prior tasks, a phenomenon known as forgetting. Traditionally, mitigating forgetting has required replaying stored exemplars from p…
Identity-Robust Language Model Generation via Content Integrity Preservation
Miao Zhang, Kelly Chen, Md Mehrab Tanjim +1
Large Language Model (LLM) outputs often vary across user sociodemographic attributes, leading to disparities in factual accuracy, utility, and safety, even for objective questions…
Correct Reasoning Paths Visit Shared Decision Pivots
Dongkyu Cho, Amy B. Z. Zhang, Bilel Fehri +4
Chain-of-thought (CoT) reasoning exposes the intermediate thinking process of large language models (LLMs), yet verifying those traces at scale remains unsolved. In response, we in…
Expert-guided Clinical Text Augmentation via Query-Based Model Collaboration
Dongkyu Cho, Miao Zhang, Rumi Chunara
Data augmentation is a widely used strategy to improve model robustness and generalization by enriching training datasets with synthetic examples. While large language models (LLMs…
Dealing with the Evil Twins: Improving Random Augmentation by Addressing Catastrophic Forgetting of Diverse Augmentations
Dongkyu Cho, Rumi Chunara
Data augmentation is a promising tool for enhancing out-of-distribution generalization, where the key is to produce diverse, challenging variations of the source domain via costly…
Domain Adaptation Under MNAR Missingness
Tyrel Stokes, Hyungrok Do, Saul Blecker +2
Current domain adaptation methods under missingness shift are restricted to Missing At Random (MAR) missingness mechanisms. However, in many real-world examples, the MAR assumption…
Forget Forgetting: Continual Learning in a World of Abundant Memory
Dongkyu Cho, Taesup Moon, Rumi Chunara +2
Continual learning (CL) has traditionally focused on minimizing exemplar memory, a constraint often misaligned with modern systems where GPU time, not storage, is the primary bottl…
Disparate Effect Of Missing Mediators On Transportability of Causal Effects
Vishwali Mhasawade, Rumi Chunara
Transported mediation effects provide an avenue to understand how upstream interventions (such as improved neighborhood conditions like green spaces) would work differently when ap…
Configurable Fairness: Direct Optimization of Parity Metrics via Vision-Language Models
Miao Zhang, Rumi Chunara
Performance disparities of image recognition across demographic groups are known to exist in deep learning-based models, due to imbalanced group representations or spurious correla…
Generalization in Healthcare AI: Evaluation of a Clinical Large Language Model
Salman Rahman, Lavender Yao Jiang, Saadia Gabriel +3
Advances in large language models (LLMs) provide new opportunities in healthcare for improved patient care, clinical decision-making, and enhancement of physician and administrator…
Impact on Public Health Decision Making by Utilizing Big Data Without Domain Knowledge
Miao Zhang, Salman Rahman, Vishwali Mhasawade +1
New data sources, and artificial intelligence (AI) methods to extract information from them are becoming plentiful, and relevant to decision making in many societal applications. A…
Understanding Disparities in Post Hoc Machine Learning Explanation
Vishwali Mhasawade, Salman Rahman, Zoe Haskell-Craig +1
Previous work has highlighted that existing post-hoc explanation methods exhibit disparities in explanation fidelity (across 'race' and 'gender' as sensitive attributes), and while…
A Brief Tutorial on Sample Size Calculations for Fairness Audits
Harvineet Singh, Fan Xia, Mi-Ok Kim +3
In fairness audits, a standard objective is to detect whether a given algorithm performs substantially differently between subgroups. Properly powering the statistical analysis of…
Mitigating Urban-Rural Disparities in Contrastive Representation Learning with Satellite Imagery
Miao Zhang, Rumi Chunara
Satellite imagery is being leveraged for many societally critical tasks across climate, economics, and public health. Yet, because of heterogeneity in landscapes (e.g. how a road l…
Data science in public health: building next generation capacity
Nicholas Mirin, Heather Mattie, Latifa Jackson +2
Rapidly evolving technology, data and analytic landscapes are permeating many fields and professions. In public health, the need for data science skills including data literacy is…
Segmenting across places: The need for fair transfer learning with satellite imagery
Miao Zhang, Harvineet Singh, Lazarus Chok +1
The increasing availability of high-resolution satellite imagery has enabled the use of machine learning to support land-cover measurement and inform policy-making. However, labell…
Uncertainty as a Form of Transparency: Measuring, Communicating, and Using Uncertainty
Umang Bhatt, Javier Antorán, Yunfeng Zhang +12
Algorithmic transparency entails exposing system properties to various stakeholders for purposes that include understanding, improving, and contesting predictions. Until now, most…
Causal Multi-Level Fairness
Vishwali Mhasawade, Rumi Chunara
Algorithmic systems are known to impact marginalized groups severely, and more so, if all sources of bias are not considered. While work in algorithmic fairness to-date has primari…
Machine Learning in Population and Public Health
Vishwali Mhasawade, Yuan Zhao, Rumi Chunara
Research in population and public health focuses on the mechanisms between different cultural, social, and environmental factors and their effect on the health, of not just individ…
Quasi-experimental Designs for Assessing Response on Social Media to Policy Changes
Yijun Tian, Rumi Chunara
Regulation of tobacco products is rapidly evolving. Understanding public sentiment in response to changes is very important as authorities assess how to effectively protect populat…
No computation without representation: Avoiding data and algorithm biases through diversity
Caitlin Kuhlman, Latifa Jackson, Rumi Chunara
The emergence and growth of research on issues of ethics in AI, and in particular algorithmic fairness, has roots in an essential observation that structural inequalities in societ…
Fairness Violations and Mitigation under Covariate Shift
Harvineet Singh, Rina Singh, Vishwali Mhasawade +1
We study the problem of learning fair prediction models for unseen test sets distributed differently from the train set. Stability against changes in data distribution is an import…