High quality annotations are increasingly a bottleneck in the explosively growing machine learning ecosystem. Scalable evaluation methods that avoid costly annotation have therefore become an important research ambition. Many hope to use strong existing models in lieu of costly labels to provide cheap model evaluations. Unfortunately, this method of using models as judges introduces biases, such as self-preferencing, that can distort model comparisons. An emerging family of debiasing tools promises to fix these issues by using a few high quality labels to debias a large number of model judgments. In this paper, we study how far such debiasing methods, in principle, can go. Our main result shows that when the judge is no more accurate than the evaluated model, no debiasing method can decrease the required amount of ground truth labels by more than half. Our result speaks to the severe limitations of the LLM-as-a-judge paradigm at the evaluation frontier where the goal is to assess newly released models that are possibly better than the judge. Through an empirical evaluation, we demonstrate that the sample size savings achievable in practice are even more modest than what our theoretical limit suggests. Along the way, our work provides new observations about debiasing methods for model evaluation, and points out promising avenues for future work.

We study a fundamental problem in the evaluation of large language models that we call training on the test task. Unlike wrongful practices like training on the test data, leakage, or data contamination, training on the test task is not a malpractice. Rather, the term describes a growing set of techniques to include task-relevant data in the pretraining stage of a language model. We demonstrate that training on the test task confounds both relative model evaluations and claims about emergent capabilities. We argue that the seeming superiority of one model family over another may be explained by a different degree of training on the test task. To this end, we propose an effective method to adjust for training on the test task by fine-tuning each model under comparison on the same task-relevant data before evaluation. We then show that instances of emergent behavior largely vanish once we adjust for training on the test task. This also applies to reported instances of emergent behavior that cannot be explained by the choice of evaluation metric. Our work promotes a new perspective on the evaluation of large language models with broad implications for benchmarking and the study of emergent capabilities.

We study the predictability of online speech on social media, and whether predictability improves with information outside a user's own posts. Recent work suggests that the predictive information contained in posts written by a user's peers can surpass that of the user's own posts. Motivated by the success of large language models, we empirically test this hypothesis. We define unpredictability as a measure of the model's uncertainty, i.e., its negative log-likelihood on future tokens given context. As the basis of our study, we collect a corpus of 6.25M posts from more than five thousand X (previously Twitter) users and their peers. Across three large language models ranging in size from 1 billion to 70 billion parameters, we find that predicting a user's posts from their peers' posts performs poorly. Moreover, the value of the user's own posts for prediction is consistently higher than that of their peers'. Across the board, we find that the predictability of social media posts remains low, comparable to predicting financial news without context. We extend our investigation with a detailed analysis about the causes of unpredictability and the robustness of our findings. Specifically, we observe that a significant amount of predictive uncertainty comes from hashtags and @-mentions. Moreover, our results replicate if instead of prompting the model with additional context, we finetune on additional context.

Algorithmic predictions are emerging as a promising solution concept for efficiently allocating societal resources. Fueling their use is an underlying assumption that such systems are necessary to identify individuals for interventions. We propose a principled framework for assessing this assumption: Using a simple mathematical model, we evaluate the efficacy of prediction-based allocations in settings where individuals belong to larger units such as hospitals, neighborhoods, or schools. We find that prediction-based allocations outperform baseline methods using aggregate unit-level statistics only when between-unit inequality is low and the intervention budget is high. Our results hold for a wide range of settings for the price of prediction, treatment effect heterogeneity, and unit-level statistics' learnability. Combined, we highlight the potential limits to improving the efficacy of interventions through prediction.

We examine multi-task benchmarks in machine learning through the lens of social choice theory. We draw an analogy between benchmarks and electoral systems, where models are candidates and tasks are voters. This suggests a distinction between cardinal and ordinal benchmark systems. The former aggregate numerical scores into one model ranking; the latter aggregate rankings for each task. We apply Arrow's impossibility theorem to ordinal benchmarks to highlight the inherent limitations of ordinal systems, particularly their sensitivity to the inclusion of irrelevant models. Inspired by Arrow's theorem, we empirically demonstrate a strong trade-off between diversity and sensitivity to irrelevant changes in existing multi-task benchmarks. Our result is based on new quantitative measures of diversity and sensitivity that we introduce. Sensitivity quantifies the impact that irrelevant changes to tasks have on a benchmark. Diversity captures the degree of disagreement in model rankings across tasks. We develop efficient approximation algorithms for both measures, as exact computation is computationally challenging. Through extensive experiments on seven cardinal benchmarks and eleven ordinal benchmarks, we demonstrate a clear trade-off between diversity and stability: The more diverse a multi-task benchmark, the more sensitive to trivial changes it is. Additionally, we show that the aggregated rankings of existing benchmarks are highly unstable under irrelevant changes. The codes and data are available at https://socialfoundations.github.io/benchbench/.

We introduce ImageNot, a dataset designed to match the scale of ImageNet while differing drastically in other aspects. We show that key model architectures developed for ImageNet over the years rank identically when trained and evaluated on ImageNot to how they rank on ImageNet. This is true when training models from scratch or fine-tuning them. Moreover, the relative improvements of each model over earlier models strongly correlate in both datasets. We further give evidence that ImageNot has a similar utility as ImageNet for transfer learning purposes. Our work demonstrates a surprising degree of external validity in the relative performance of image classification models. This stands in contrast with absolute accuracy numbers that typically drop sharply even under small changes to a dataset.

We study how well machine learning models trained on causal features generalize across domains. We consider 16 prediction tasks on tabular datasets covering applications in health, employment, education, social benefits, and politics. Each dataset comes with multiple domains, allowing us to test how well a model trained in one domain performs in another. For each prediction task, we select features that have a causal influence on the target of prediction. Our goal is to test the hypothesis that models trained on causal features generalize better across domains. Without exception, we find that predictors using all available features, regardless of causality, have better in-domain and out-of-domain accuracy than predictors using causal features. Moreover, even the absolute drop in accuracy from one domain to the other is no better for causal predictors than for models that use all features. If the goal is to generalize to new domains, practitioners might as well train the best possible model on all available features.

We study how to best spend a budget of noisy labels to compare the accuracy of two binary classifiers. It's common practice to collect and aggregate multiple noisy labels for a given data point into a less noisy label via a majority vote. We prove a theorem that runs counter to conventional wisdom. If the goal is to identify the better of two classifiers, we show it's best to spend the budget on collecting a single label for more samples. Our result follows from a non-trivial application of Cram\'er's theorem, a staple in the theory of large deviations. We discuss the implications of our work for the design of machine learning benchmarks, where they overturn some time-honored recommendations. In addition, our results provide sample size bounds superior to what follows from Hoeffding's bound.

Predictions in the social world generally influence the target of prediction, a phenomenon known as performativity. Self-fulfilling and self-negating predictions are examples of performativity. Of fundamental importance to economics, finance, and the social sciences, the notion has been absent from the development of machine learning. In machine learning applications, performativity often surfaces as distribution shift. A predictive model deployed on a digital platform, for example, influences consumption and thereby changes the data-generating distribution. We survey the recently founded area of performative prediction that provides a definition and conceptual framework to study performativity in machine learning. A consequence of performative prediction is a natural equilibrium notion that gives rise to new optimization challenges. Another consequence is a distinction between learning and steering, two mechanisms at play in performative prediction. The notion of steering is in turn intimately related to questions of power in digital markets. We review the notion of performative power that gives an answer to the question how much a platform can steer participants through its predictions. We end on a discussion of future directions, such as the role that performativity plays in contesting algorithmic systems.

Seven years ago, researchers proposed a postprocessing method to equalize the error rates of a model across different demographic groups. The work launched hundreds of papers purporting to improve over the postprocessing baseline. We empirically evaluate these claims through thousands of model evaluations on several tabular datasets. We find that the fairness-accuracy Pareto frontier achieved by postprocessing contains all other methods we were feasibly able to evaluate. In doing so, we address two common methodological errors that have confounded previous observations. One relates to the comparison of methods with different unconstrained base models. The other concerns methods achieving different levels of constraint relaxation. At the heart of our study is a simple idea we call unprocessing that roughly corresponds to the inverse of postprocessing. Unprocessing allows for a direct comparison of methods using different underlying models and levels of relaxation.