Predicting the Performance of Black-box LLMs through Self-Queries

As large language models (LLMs) are increasingly relied on in AI systems, predicting when they make mistakes is crucial. While a great deal of work in the field uses internal representations to interpret model behavior, these representations are inaccessible when given solely black-box access through an API. In this paper, we extract features of LLMs in a black-box manner by using follow-up prompts and taking the probabilities of different responses as representations to train reliable predictors of model behavior. We demonstrate that training a linear model on these low-dimensional representations produces reliable and generalizable predictors of model performance at the instance level (e.g., if a particular generation correctly answers a question). Remarkably, these can often outperform white-box linear predictors that operate over a model's hidden state or the full distribution over its vocabulary. In addition, we demonstrate that these extracted features can be used to evaluate more nuanced aspects of a language model's state. For instance, they can be used to distinguish between a clean version of GPT-4o-mini and a version that has been influenced via an adversarial system prompt that answers question-answering tasks incorrectly or introduces bugs into generated code. Furthermore, they can reliably distinguish between different model architectures and sizes, enabling the detection of misrepresented models provided through an API (e.g., identifying if GPT-3.5 is supplied instead of GPT-4o-mini).

Finetuning CLIP to Reason about Pairwise Differences

Vision-language models (VLMs) such as CLIP are trained via contrastive learning between text and image pairs, resulting in aligned image and text embeddings that are useful for many downstream tasks. A notable drawback of CLIP, however, is that the resulting embedding space seems to lack some of the structure of their purely text-based alternatives. For instance, while text embeddings have been long noted to satisfy \emph{analogies} in embedding space using vector arithmetic, CLIP has no such property. In this paper, we propose an approach to natively train CLIP in a contrastive manner to reason about differences in embedding space. We finetune CLIP so that the differences in image embedding space correspond to \emph{text descriptions of the image differences}, which we synthetically generate with large language models on image-caption paired datasets. We first demonstrate that our approach yields significantly improved capabilities in ranking images by a certain attribute (e.g., elephants are larger than cats), which is useful in retrieval or constructing attribute-based classifiers, and improved zeroshot classification performance on many downstream image classification tasks. In addition, our approach enables a new mechanism for inference that we refer to as comparative prompting, where we leverage prior knowledge of text descriptions of differences between classes of interest, achieving even larger performance gains in classification. Finally, we illustrate that the resulting embeddings obey a larger degree of geometric properties in embedding space, such as in text-to-image generation.

Auditing Fairness under Unobserved Confounding

A fundamental problem in decision-making systems is the presence of inequity across demographic lines. However, inequity can be difficult to quantify, particularly if our notion of equity relies on hard-to-measure notions like risk (e.g., equal access to treatment for those who would die without it). Auditing such inequity requires accurate measurements of individual risk, which is difficult to estimate in the realistic setting of unobserved confounding. In the case that these unobservables "explain" an apparent disparity, we may understate or overstate inequity. In this paper, we show that one can still give informative bounds on allocation rates among high-risk individuals, even while relaxing or (surprisingly) even when eliminating the assumption that all relevant risk factors are observed. We utilize the fact that in many real-world settings (e.g., the introduction of a novel treatment) we have data from a period prior to any allocation, to derive unbiased estimates of risk. We demonstrate the effectiveness of our framework on a real-world study of Paxlovid allocation to COVID-19 patients, finding that observed racial inequity cannot be explained by unobserved confounders of the same strength as important observed covariates.

Bayesian Neural Networks with Domain Knowledge Priors

Bayesian neural networks (BNNs) have recently gained popularity due to their ability to quantify model uncertainty. However, specifying a prior for BNNs that captures relevant domain knowledge is often extremely challenging. In this work, we propose a framework for integrating general forms of domain knowledge (i.e., any knowledge that can be represented by a loss function) into a BNN prior through variational inference, while enabling computationally efficient posterior inference and sampling. Specifically, our approach results in a prior over neural network weights that assigns high probability mass to models that better align with our domain knowledge, leading to posterior samples that also exhibit this behavior. We show that BNNs using our proposed domain knowledge priors outperform those with standard priors (e.g., isotropic Gaussian, Gaussian process), successfully incorporating diverse types of prior information such as fairness, physics rules, and healthcare knowledge and achieving better predictive performance. We also present techniques for transferring the learned priors across different model architectures, demonstrating their broad utility across various settings.

Understanding prompt engineering may not require rethinking generalization

Zero-shot learning in prompted vision-language models, the practice of crafting prompts to build classifiers without an explicit training process, has achieved impressive performance in many settings. This success presents a seemingly surprising observation: these methods suffer relatively little from overfitting, i.e., when a prompt is manually engineered to achieve low error on a given training set (thus rendering the method no longer actually zero-shot), the approach still performs well on held-out test data. In this paper, we show that we can explain such performance well via recourse to classical PAC-Bayes bounds. Specifically, we show that the discrete nature of prompts, combined with a PAC-Bayes prior given by a language model, results in generalization bounds that are remarkably tight by the standards of the literature: for instance, the generalization bound of an ImageNet classifier is often within a few percentage points of the true test error. We demonstrate empirically that this holds for existing handcrafted prompts and prompts generated through simple greedy search. Furthermore, the resulting bound is well-suited for model selection: the models with the best bound typically also have the best test performance. This work thus provides a possible justification for the widespread practice of prompt engineering, even if it seems that such methods could potentially overfit the training data.

Learning with Explanation Constraints

While supervised learning assumes the presence of labeled data, we may have prior information about how models should behave. In this paper, we formalize this notion as learning from explanation constraints and provide a learning theoretic framework to analyze how such explanations can improve the learning of our models. For what models would explanations be helpful? Our first key contribution addresses this question via the definition of what we call EPAC models (models that satisfy these constraints in expectation over new data), and we analyze this class of models using standard learning theoretic tools. Our second key contribution is to characterize these restrictions (in terms of their Rademacher complexities) for a canonical class of explanations given by gradient information for linear models and two layer neural networks. Finally, we provide an algorithmic solution for our framework, via a variational approximation that achieves better performance and satisfies these constraints more frequently, when compared to simpler augmented Lagrangian methods to incorporate these explanations. We demonstrate the benefits of our approach over a large array of synthetic and real-world experiments.

Improving self-supervised representation learning via sequential adversarial masking

Recent methods in self-supervised learning have demonstrated that masking-based pretext tasks extend beyond NLP, serving as useful pretraining objectives in computer vision. However, existing approaches apply random or ad hoc masking strategies that limit the difficulty of the reconstruction task and, consequently, the strength of the learnt representations. We improve upon current state-of-the-art work in learning adversarial masks by proposing a new framework that generates masks in a sequential fashion with different constraints on the adversary. This leads to improvements in performance on various downstream tasks, such as classification on ImageNet100, STL10, and CIFAR10/100 and segmentation on Pascal VOC. Our results further demonstrate the promising capabilities of masking-based approaches for SSL in computer vision.

Losses over Labels: Weakly Supervised Learning via Direct Loss Construction

Owing to the prohibitive costs of generating large amounts of labeled data, programmatic weak supervision is a growing paradigm within machine learning. In this setting, users design heuristics that provide noisy labels for subsets of the data. These weak labels are combined (typically via a graphical model) to form pseudolabels, which are then used to train a downstream model. In this work, we question a foundational premise of the typical weakly supervised learning pipeline: given that the heuristic provides all ``label" information, why do we need to generate pseudolabels at all? Instead, we propose to directly transform the heuristics themselves into corresponding loss functions that penalize differences between our model and the heuristic. By constructing losses directly from the heuristics, we can incorporate more information than is used in the standard weakly supervised pipeline, such as how the heuristics make their decisions, which explicitly informs feature selection during training. We call our method Losses over Labels (LoL) as it creates losses directly from heuristics without going through the intermediate step of a label. We show that LoL improves upon existing weak supervision methods on several benchmark text and image classification tasks and further demonstrate that incorporating gradient information leads to better performance on almost every task.

Label Propagation with Weak Supervision

Semi-supervised learning and weakly supervised learning are important paradigms that aim to reduce the growing demand for labeled data in current machine learning applications. In this paper, we introduce a novel analysis of the classical label propagation algorithm (LPA) (Zhu & Ghahramani, 2002) that moreover takes advantage of useful prior information, specifically probabilistic hypothesized labels on the unlabeled data. We provide an error bound that exploits both the local geometric properties of the underlying graph and the quality of the prior information. We also propose a framework to incorporate multiple sources of noisy information. In particular, we consider the setting of weak supervision, where our sources of information are weak labelers. We demonstrate the ability of our approach on multiple benchmark weakly supervised classification tasks, showing improvements upon existing semi-supervised and weakly supervised methods.