Lucas Monteiro Paes, Dennis Wei, Hyo Jin Do, Hendrik Strobelt, Ronny Luss, Amit Dhurandhar, Manish Nagireddy, Karthikeyan Natesan Ramamurthy, Prasanna Sattigeri, Werner Geyer, Soumya Ghosh. Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2025.

Image search and retrieval tasks can perpetuate harmful stereotypes, erase cultural identities, and amplify social disparities. Current approaches to mitigate these representational harms balance the number of retrieved items across population groups defined by a small number of (often binary) attributes. However, most existing methods overlook intersectional groups determined by combinations of group attributes, such as gender, race, and ethnicity. We introduce Multi-Group Proportional Representation (MPR), a novel metric that measures representation across intersectional groups. We develop practical methods for estimating MPR, provide theoretical guarantees, and propose optimization algorithms to ensure MPR in retrieval. We demonstrate that existing methods optimizing for equal and proportional representation metrics may fail to promote MPR. Crucially, our work shows that optimizing MPR yields more proportional representation across multiple intersectional groups specified by a rich function class, often with minimal compromise in retrieval accuracy. Code is provided at https://github.com/alex-oesterling/multigroup-proportional-representation.

Feature attribution methods explain black-box machine learning (ML) models by assigning importance scores to input features. These methods can be computationally expensive for large ML models. To address this challenge, there have been increasing efforts to develop amortized explainers, where a ML model is trained to efficiently approximate computationally expensive feature attribution scores. Despite their efficiency, amortized explainers can produce misleading explanations. In this paper, we propose selective explanations to (i) detect when amortized explainers generate inaccurate explanations and (ii) improve the approximation of the explanation using a technique we call explanations with initial guess. Selective explanations allow practitioners to specify the fraction of samples that receive explanations with initial guess, offering a principled way to bridge the gap between amortized explainers (one inference) and more computationally costly approximations (multiple inferences). Our experiments on various models and datasets demonstrate that feature attributions via selective explanations strike a favorable balance between explanation quality and computational efficiency.

Accurately predicting the volume of amniotic fluid is fundamental to assessing pregnancy risks, though the task usually requires many hours of laborious work by medical experts. In this paper, we present AmnioML, a machine learning solution that leverages deep learning and conformal prediction to output fast and accurate volume estimates and segmentation masks from fetal MRIs with Dice coefficient over 0.9. Also, we make available a novel, curated dataset for fetal MRIs with 853 exams and benchmark the performance of many recent deep learning architectures. In addition, we introduce a conformal prediction tool that yields narrow predictive intervals with theoretically guaranteed coverage, thus aiding doctors in detecting pregnancy risks and saving lives. A successful case study of AmnioML deployed in a medical setting is also reported. Real-world clinical benefits include up to 20x segmentation time reduction, with most segmentations deemed by doctors as not needing any further manual refinement. Furthermore, AmnioML's volume predictions were found to be highly accurate in practice, with mean absolute error below 56mL and tight predictive intervals, showcasing its impact in reducing pregnancy complications.

The Rashomon effect in machine learning (ML) occurs when multiple distinct models achieve similar average loss on a given learning task. The set of all models with expected loss smaller than ϵ is called the Rashomon set. The characterization of this set for a given learning task allows searching for models that satisfy additional constraints (e.g., interpretability, fairness) without compromising accuracy. Though folklore treats the Rashomon set as the collection of all indistinguishable "good" models, there are no established theoretical guarantees that models in this set are statistically indistinguishable. We fill this gap by proposing a hypothesis test framework to choose the best-performing model between two elements in the Rashomon set and derive lower and upper bounds for its probability of error. Specifically, we prove that for any ϵ > 0 if the data set has less than $O\left( {{{[\varepsilon {\text{log}}\left( {\varepsilon /\left( {1 - \varepsilon } \right)} \right)]}^{ - 1}}} \right)$ instances, models in the Rashomon set are statistically indistinguishable and the Rashomon effect is inevitable. Additionally, our bounds can guide data scientists to choose an ϵ that generates a Rashomon set so that any two models in it are indistinguishable.

Machine learning models are often personalized by using group attributes that encode personal characteristics (e.g., sex, age group, HIV status). In such settings, individuals expect to receive more accurate predictions in return for disclosing group attributes to the personalized model. We study when we can tell that a personalized model upholds this principle for every group who provides personal data. We introduce a metric called the benefit of personalization (BoP) to measure the smallest gain in accuracy that any group expects to receive from a personalized model. We describe how the BoP can be used to carry out basic routines to audit a personalized model, including: (i) hypothesis tests to check that a personalized model improves performance for every group; (ii) estimation procedures to bound the minimum gain in personalization. We characterize the reliability of these routines in a finite-sample regime and present minimax bounds on both the probability of error for BoP hypothesis tests and the mean-squared error of BoP estimates. Our results show that we can only claim that personalization improves performance for each group who provides data when we explicitly limit the number of group attributes used by a personalized model. In particular, we show that it is impossible to reliably verify that a personalized classifier with $k \geq 19$ binary group attributes will benefit every group who provides personal data using a dataset of $n = 8\times10^9$ samples -- one for each person in the world.