Multimodal Large Language Models (MLLMs) hold great promise for advanced reasoning at the intersection of text and images, yet they have not fully realized this potential. MLLMs typically integrate an LLM, a vision encoder, and a connector that maps the vision encoder's embeddings into the LLM's text embedding space. Although each component is pretrained on massive datasets with billions of samples, the entire multimodal model is typically trained on only thousands (or a few million) samples, which can result in weak performance on complex reasoning tasks. To address these shortcomings, instead of relying on extensive labeled datasets for fine-tuning, we propose a Test-Time Warmup method that adapts the MLLM per test instance by leveraging data from weakly supervised auxiliary tasks. With our approach, we observe a relative performance improvement of 4.03% on MMMU, 5.28% on VQA-Rad, and 1.63% on GQA on the Llama-Vision-Instruct model. Our method demonstrates that 'warming up' before inference can enhance MLLMs' robustness across diverse reasoning tasks.

Large language models are increasingly used to support high-stakes decisions, potentially influencing who is granted bail or receives a loan. Naive chain-of-thought sampling can improve average decision accuracy, but has also been shown to amplify unfair bias. To address this challenge and enable the trustworthy use of reasoning models in high-stakes decision-making, we propose a framework for training a generalizable Fairness Reward Model (FRM). Our model assigns a fairness score to LLM reasoning, enabling the system to down-weight biased trajectories and favor equitable ones when aggregating decisions across reasoning chains. We show that a single Fairness Reward Model, trained on weakly supervised, LLM-annotated examples of biased versus unbiased reasoning, transfers across tasks, domains, and model families without additional fine-tuning. Applied to real-world decision-making tasks including recidivism prediction and social media moderation, we show that our approach consistently improves fairness while matching, or even surpassing, baseline accuracy.

As machine learning models grow increasingly competent, their predictions can supplement scarce or expensive data in various important domains. In support of this paradigm, algorithms have emerged to combine a small amount of high-fidelity observed data with a much larger set of imputed model outputs to estimate some quantity of interest. Yet current hybrid-inference tools target only means or single quantiles, limiting their applicability for many critical domains and use cases. We present QuEst, a principled framework to merge observed and imputed data to deliver point estimates and rigorous confidence intervals for a wide family of quantile-based distributional measures. QuEst covers a range of measures, from tail risk (CVaR) to population segments such as quartiles, that are central to fields such as economics, sociology, education, medicine, and more. We extend QuEst to multidimensional metrics, and introduce an additional optimization technique to further reduce variance in this and other hybrid estimators. We demonstrate the utility of our framework through experiments in economic modeling, opinion polling, and language model auto-evaluation.

Generative AI (GenAI) models present new challenges in regulating against discriminatory behavior. In this paper, we argue that GenAI fairness research still has not met these challenges; instead, a significant gap remains between existing bias assessment methods and regulatory goals. This leads to ineffective regulation that can allow deployment of reportedly fair, yet actually discriminatory, GenAI systems. Towards remedying this problem, we connect the legal and technical literature around GenAI bias evaluation and identify areas of misalignment. Through four case studies, we demonstrate how this misalignment between fairness testing techniques and regulatory goals can result in discriminatory outcomes in real-world deployments, especially in adaptive or complex environments. We offer practical recommendations for improving discrimination testing to better align with regulatory goals and enhance the reliability of fairness assessments in future deployments.

The recent explosion in the capabilities of large language models has led to a wave of interest in how best to prompt a model to perform a given task. While it may be tempting to simply choose a prompt based on average performance on a validation set, this can lead to a deployment where unexpectedly poor responses are generated, especially for the worst-off users. To mitigate this prospect, we propose Prompt Risk Control, a lightweight framework for selecting a prompt based on rigorous upper bounds on families of informative risk measures. We offer methods for producing bounds on a diverse set of metrics, including quantities that measure worst-case responses and disparities in generation quality across the population of users. In addition, we extend the underlying statistical bounding techniques to accommodate the possibility of distribution shifts in deployment. Experiments on applications such as open-ended chat, medical question summarization, and code generation highlight how such a framework can foster responsible deployment by reducing the risk of the worst outcomes.

Explicit finite-sample statistical guarantees on model performance are an important ingredient in responsible machine learning. Previous work has focused mainly on bounding either the expected loss of a predictor or the probability that an individual prediction will incur a loss value in a specified range. However, for many high-stakes applications, it is crucial to understand and control the dispersion of a loss distribution, or the extent to which different members of a population experience unequal effects of algorithmic decisions. We initiate the study of distribution-free control of statistical dispersion measures with societal implications and propose a simple yet flexible framework that allows us to handle a much richer class of statistical functionals beyond previous work. Our methods are verified through experiments in toxic comment detection, medical imaging, and film recommendation.

Rigorous guarantees about the performance of predictive algorithms are necessary in order to ensure their responsible use. Previous work has largely focused on bounding the expected loss of a predictor, but this is not sufficient in many risk-sensitive applications where the distribution of errors is important. In this work, we propose a flexible framework to produce a family of bounds on quantiles of the loss distribution incurred by a predictor. Our method takes advantage of the order statistics of the observed loss values rather than relying on the sample mean alone. We show that a quantile is an informative way of quantifying predictive performance, and that our framework applies to a variety of quantile-based metrics, each targeting important subsets of the data distribution. We analyze the theoretical properties of our proposed method and demonstrate its ability to rigorously control loss quantiles on several real-world datasets.

Knowledge Graph (KG) embeddings provide a low-dimensional representation of entities and relations of a Knowledge Graph and are used successfully for various applications such as question answering and search, reasoning, inference, and missing link prediction. However, most of the existing KG embeddings only consider the network structure of the graph and ignore the semantics and the characteristics of the underlying ontology that provides crucial information about relationships between entities in the KG. Recent efforts in this direction involve learning embeddings for a Description Logic (logical underpinning for ontologies) named EL++. However, such methods consider all the relations defined in the ontology to be one-to-one which severely limits their performance and applications. We provide a simple and effective solution to overcome this shortcoming that allows such methods to consider many-to-many relationships while learning embedding representations. Experiments conducted using three different EL++ ontologies show substantial performance improvement over five baselines. Our proposed solution also paves the way for learning embedding representations for even more expressive description logics such as SROIQ.

Real world learning scenarios involve a nonstationary distribution of classes with sequential dependencies among the samples, in contrast to the standard machine learning formulation of drawing samples independently from a fixed, typically uniform distribution. Furthermore, real world interactions demand learning on-the-fly from few or no class labels. In this work, we propose an unsupervised model that simultaneously performs online visual representation learning and few-shot learning of new categories without relying on any class labels. Our model is a prototype-based memory network with a control component that determines when to form a new class prototype. We formulate it as an online Gaussian mixture model, where components are created online with only a single new example, and assignments do not have to be balanced, which permits an approximation to natural imbalanced distributions from uncurated raw data. Learning includes a contrastive loss that encourages different views of the same image to be assigned to the same prototype. The result is a mechanism that forms categorical representations of objects in nonstationary environments. Experiments show that our method can learn from an online stream of visual input data and is significantly better at category recognition compared to state-of-the-art self-supervised learning methods.

Existing approaches to few-shot learning deal with tasks that have persistent, rigid notions of classes. Typically, the learner observes data only from a fixed number of classes at training time and is asked to generalize to a new set of classes at test time. Two examples from the same class would always be assigned the same labels in any episode. In this work, we consider a realistic setting where the similarities between examples can change from episode to episode depending on the task context, which is not given to the learner. We define new benchmark datasets for this flexible few-shot scenario, where the tasks are based on images of faces (Celeb-A), shoes (Zappos50K), and general objects (ImageNet-with-Attributes). While classification baselines and episodic approaches learn representations that work well for standard few-shot learning, they suffer in our flexible tasks as novel similarity definitions arise during testing. We propose to build upon recent contrastive unsupervised learning techniques and use a combination of instance and class invariance learning, aiming to obtain general and flexible features. We find that our approach performs strongly on our new flexible few-shot learning benchmarks, demonstrating that unsupervised learning obtains more generalizable representations.