Dynabench comprises four dynamic tasks with multiple rounds of datasets that will grow over time. Given that here we have to be able to evaluate a wide variety of models, both in the loop and outside of it, we employ a black box post hoc approach, i.e., one that can be applied post-data collection to existing data, on any uploaded model, without requiring anything other than its predictions. One straightforward way to measure fairness then, is to apply clearly delimited, heuristic perturbations to existing evaluation datasets, and measure whether performance drops. Such an approach is similar to recent works that use grammars to heuristically generate pairs of examples varying in gender [58] and/or race [67] in that they utilize predefined lists of words. However, because we also want to ensure minimal consequences on our classification labels, we adopted an approach that is more targeted than grammars and also preserves the original input data distribution: we replace each word in the input data that has a clear signal about race/ethnicity and/or gender identity with a similar word referring to another group, rerun inference, and measure how many labels flipped (i.e., the difference in microaverage accuracy).

As libraries explore large language models (LLMs) for use in virtual reference services, a key question arises: Can LLMs serve all users equitably, regardless of demographics or social status? While they offer great potential for scalable support, LLMs may also reproduce societal biases embedded in their training data, risking the integrity of libraries' commitment to equitable service. To address this concern, we evaluate whether LLMs differentiate responses across user identities by prompting six state-of-the-art LLMs to assist patrons differing in sex, race/ethnicity, and institutional role. We find no evidence of differentiation by race or ethnicity, and only minor evidence of stereotypical bias against women in one model. LLMs demonstrate nuanced accommodation of institutional roles through the use of linguistic choices related to formality, politeness, and domain-specific vocabularies, reflecting professional norms rather than discriminatory treatment. These findings suggest that current LLMs show a promising degree of readiness to support equitable and contextually appropriate communication in academic library reference services.

Vision-language models trained on large-scale multimodal datasets show strong demographic biases, but the role of training data in producing these biases remains unclear. A major barrier has been the lack of demographic annotations in web-scale datasets such as LAION-400M. We address this gap by creating person-centric annotations for the full dataset, including over 276 million bounding boxes, perceived gender and race/ethnicity labels, and automatically generated captions. These annotations are produced through validated automatic labeling pipelines combining object detection, multimodal captioning, and finetuned classifiers. Using them, we uncover demographic imbalances and harmful associations, such as the disproportionate linking of men and individuals perceived as Black or Middle Eastern with crime-related and negative content. We also show that 60-70% of gender bias in CLIP and Stable Diffusion can be linearly explained by direct co-occurrences in the data. Our resources establish the first large-scale empirical link between dataset composition and downstream model bias.

The present research tackles the difficulty of predicting osteoporosis risk via machine learning (ML) approaches, emphasizing the use of explainable artificial intelligence (XAI) to improve model transparency. Osteoporosis is a significant public health concern, sometimes remaining untreated owing to its asymptomatic characteristics, and early identification is essential to avert fractures. The research assesses six machine learning classifiers: Random Forest, Logistic Regression, XGBoost, AdaBoost, LightGBM, and Gradient Boosting and utilizes a dataset based on clinical, demographic, and lifestyle variables. The models are refined using GridSearchCV to calibrate hyperparameters, with the objective of enhancing predictive efficacy. XGBoost had the greatest accuracy (91%) among the evaluated models, surpassing others in precision (0.92), recall (0.91), and F1-score (0.90). The research further integrates XAI approaches, such as SHAP, LIME, and Permutation Feature Importance, to elucidate the decision-making process of the optimal model. The study indicates that age is the primary determinant in forecasting osteoporosis risk, followed by hormonal alterations and familial history. These results corroborate clinical knowledge and affirm the models' therapeutic significance. The research underscores the significance of explainability in machine learning models for healthcare applications, guaranteeing that physicians can rely on the system's predictions. The report ultimately proposes directions for further research, such as validation across varied populations and the integration of supplementary biomarkers for enhanced predictive accuracy.

In the United States, schizophrenia (SCZ) carries a race and sex disparity that may be explained by clinician bias - a belief held by a clinician about a patient that prevents impartial clinical decision making. The emergency department (ED) is marked by higher rates of stress that lead to clinicians relying more on implicit biases during decision making. In this work, we considered a large cohort of psychiatric patients in the ED from the Mount Sinai Health System (MSHS) in New York City to investigate the effects of clinician bias on SCZ diagnosis while controlling for known risk factors and patient sociodemographic information. Clinician bias was quantified as the ratio of negative to total sentences within a patient's first ED note. We utilized a logistic regression to predict SCZ diagnosis given patient race, sex, age, history of trauma or substance use disorder, and the ratio of negative sentences. Our findings showed that an increased ratio of negative sentences is associated with higher odds of obtaining a SCZ diagnosis [OR (95% CI)=1.408 (1.361-1.456)]. Identifying as male [OR (95% CI)=1.112 (1.055-1.173)] or Black [OR (95% CI)=1.081(1.031-1.133)] increased one's odds of being diagnosed with SCZ. However, from an intersectional lens, Black female patients with high SES have the highest odds of obtaining a SCZ diagnosis [OR (95% CI)=1.629 (1.535-1.729)]. Results such as these suggest that SES does not act as a protective buffer against SCZ diagnosis in all patients, demanding more attention to the quantification of health disparities. Lastly, we demonstrated that clinician bias is operational with real world data and related to increased odds of obtaining a stigmatizing diagnosis such as SCZ.

Achieving robust performance and fairness across diverse patient populations remains a challenge in developing clinically deployable deep learning models for diagnostic imaging. Synthetic data generation has emerged as a promising strategy to address limitations in dataset scale and diversity. We introduce RoentGen-v2, a text-to-image diffusion model for chest radiographs that enables fine-grained control over both radiographic findings and patient demographic attributes, including sex, age, and race/ethnicity. RoentGen-v2 is the first model to generate clinically plausible images with demographic conditioning, facilitating the creation of a large, demographically balanced synthetic dataset comprising over 565,000 images. We use this large synthetic dataset to evaluate optimal training pipelines for downstream disease classification models. In contrast to prior work that combines real and synthetic data naively, we propose an improved training strategy that leverages synthetic data for supervised pretraining, followed by fine-tuning on real data. Through extensive evaluation on over 137,000 chest radiographs from five institutions, we demonstrate that synthetic pretraining consistently improves model performance, generalization to out-of-distribution settings, and fairness across demographic subgroups. Across datasets, synthetic pretraining led to a 6.5% accuracy increase in the performance of downstream classification models, compared to a modest 2.7% increase when naively combining real and synthetic data. We observe this performance improvement simultaneously with the reduction of the underdiagnosis fairness gap by 19.3%. These results highlight the potential of synthetic imaging to advance equitable and generalizable medical deep learning under real-world data constraints. We open source our code, trained models, and synthetic dataset at https://github.com/StanfordMIMI/RoentGen-v2 .