Continually evaluating large generative models provides a unique challenge. Often, human annotations are necessary to evaluate high-level properties of these models (e.g. in text or images). However, collecting human annotations of samples can be resource intensive, and using other machine learning systems to provide the annotations, or automatic evaluation, can introduce systematic errors into the evaluation. The Prediction Powered Inference (PPI) framework provides a way of leveraging both the statistical power of automatic evaluation and a small pool of labelled data to produce a low-variance, unbiased estimate of the quantity being evaluated for. However, most work on PPI considers a relatively sizable set of labelled samples, which is not always practical to obtain. To this end, we present two new PPI-based techniques that leverage robust regressors to produce even lower variance estimators in the few-label regime.

In this report, we introduce the Gemini 1.5 family of models, representing the next generation of highly compute-efficient multimodal models capable of recalling and reasoning over fine-grained information from millions of tokens of context, including multiple long documents and hours of video and audio. The family includes two new models: (1) an updated Gemini 1.5 Pro, which exceeds the February version on the great majority of capabilities and benchmarks; (2) Gemini 1.5 Flash, a more lightweight variant designed for efficiency with minimal regression in quality. Gemini 1.5 models achieve near-perfect recall on long-context retrieval tasks across modalities, improve the state-of-the-art in long-document QA, long-video QA and long-context ASR, and match or surpass Gemini 1.0 Ultra's state-of-the-art performance across a broad set of benchmarks. Studying the limits of Gemini 1.5's long-context ability, we find continued improvement in next-token prediction and near-perfect retrieval (>99%) up to at least 10M tokens, a generational leap over existing models such as Claude 3.0 (200k) and GPT-4 Turbo (128k). Finally, we highlight real-world use cases, such as Gemini 1.5 collaborating with professionals on completing their tasks achieving 26 to 75% time savings across 10 different job categories, as well as surprising new capabilities of large language models at the frontier; when given a grammar manual for Kalamang, a language with fewer than 200 speakers worldwide, the model learns to translate English to Kalamang at a similar level to a person who learned from the same content.

As the number of large language models (LLMs) released to the public grows, there is a pressing need to understand the safety implications associated with these models learning from third-party custom finetuning data. We explore the behavior of LLMs finetuned on noisy custom data containing unsafe content, represented by datasets that contain biases, toxicity, and harmfulness, finding that while aligned LLMs can readily learn this unsafe content, they also tend to forget it more significantly than other examples when subsequently finetuned on safer content. Drawing inspiration from the discrepancies in forgetting, we introduce the "ForgetFilter" algorithm, which filters unsafe data based on how strong the model's forgetting signal is for that data. We demonstrate that the ForgetFilter algorithm ensures safety in customized finetuning without compromising downstream task performance, unlike sequential safety finetuning. ForgetFilter outperforms alternative strategies like replay and moral self-correction in curbing LLMs' ability to assimilate unsafe content during custom finetuning, e.g. 75% lower than not applying any safety measures and 62% lower than using self-correction in toxicity score.

This report introduces a new family of multimodal models, Gemini, that exhibit remarkable capabilities across image, audio, video, and text understanding. The Gemini family consists of Ultra, Pro, and Nano sizes, suitable for applications ranging from complex reasoning tasks to on-device memory-constrained use-cases. Evaluation on a broad range of benchmarks shows that our most-capable Gemini Ultra model advances the state of the art in 30 of 32 of these benchmarks - notably being the first model to achieve human-expert performance on the well-studied exam benchmark MMLU, and improving the state of the art in every one of the 20 multimodal benchmarks we examined. We believe that the new capabilities of Gemini models in cross-modal reasoning and language understanding will enable a wide variety of use cases and we discuss our approach toward deploying them responsibly to users.

Robustness is of central importance in machine learning and has given rise to the fields of domain generalization and invariant learning, which are concerned with improving performance on a test distribution distinct from but related to the training distribution. In light of recent work suggesting an intimate connection between fairness and robustness, we investigate whether algorithms from robust ML can be used to improve the fairness of classifiers that are trained on biased data and tested on unbiased data. We apply Invariant Risk Minimization (IRM), a domain generalization algorithm that employs a causal discovery inspired method to find robust predictors, to the task of fairly predicting the toxicity of internet comments. We show that IRM achieves better out-of-distribution accuracy and fairness than Empirical Risk Minimization (ERM) methods, and analyze both the difficulties that arise when applying IRM in practice and the conditions under which IRM will likely be effective in this scenario. We hope that this work will inspire further studies of how robust machine learning methods relate to algorithmic fairness.

Standard causal discovery methods must fit a new model whenever they encounter samples from a new underlying causal graph. However, these samples often share relevant information - for instance, the dynamics describing the effects of causal relations - which is lost when following this approach. We propose Amortized Causal Discovery, a novel framework that leverages such shared dynamics to learn to infer causal relations from time-series data. This enables us to train a single, amortized model that infers causal relations across samples with different underlying causal graphs, and thus makes use of the information that is shared. We demonstrate experimentally that this approach, implemented as a variational model, leads to significant improvements in causal discovery performance, and show how it can be extended to perform well under hidden confounding.

We present local ensembles, a method for detecting extrapolation at test time in a pre-trained model. We focus on underdetermination as a key component of extrapolation: we aim to detect when many possible predictions are consistent with the training data and model class. Our method uses local second-order information to approximate the variance of predictions across an ensemble of models from the same class. We compute this approximation by estimating the norm of the component of a test point's gradient that aligns with the low-curvature directions of the Hessian, and provide a tractable method for estimating this quantity. Experimentally, we show that our method is capable of detecting when a pre-trained model is extrapolating on test data, with applications to out-of-distribution detection, detecting spurious correlates, and active learning.

In this work, we present causal directed acyclic graphs (DAGs) as a unifying framework for the recent literature on fairness in dynamical systems. We advocate for the use of causal DAGs as a tool in both designing equitable policies and estimating their impacts. By visualizing models of dynamic unfairness graphically, we expose implicit causal assumptions which can then be more easily interpreted and scrutinized by domain experts. We demonstrate that this method of reinterpretation can be used to critique the robustness of an existing model/policy, or uncover new policy evaluation questions. Causal models also enable a rich set of options for evaluating a new candidate policy without incurring the risk of implementing the policy in the real world. We close the paper with causal analyses of several models from the recent literature, and provide an in-depth case study to demonstrate the utility of causal DAGs for modeling fairness in dynamical systems.

We consider the problem of learning representations that achieve group and subgroup fairness with respect to multiple sensitive attributes. Taking inspiration from the disentangled representation learning literature, we propose an algorithm for learning compact representations of datasets that are useful for reconstruction and prediction, but are also \emph{flexibly fair}, meaning they can be easily modified at test time to achieve subgroup demographic parity with respect to multiple sensitive attributes and their conjunctions. We show empirically that the resulting encoder---which does not require the sensitive attributes for inference---enables the adaptation of a single representation to a variety of fair classification tasks with new target labels and subgroup definitions.

In many machine learning applications, there are multiple decision-makers involved, both automated and human. The interaction between these agents often goes unaddressed in algorithmic development. In this work, we explore a simple version of this interaction with a two-stage framework containing an automated model and an external decision-maker. The model can choose to say PASS, and pass the decision downstream, as explored in rejection learning. We extend this concept by proposing "learning to defer", which generalizes rejection learning by considering the effect of other agents in the decision-making process. We propose a learning algorithm which accounts for potential biases held by external decision-makers in a system. Experiments demonstrate that learning to defer can make systems not only more accurate but also less biased. Even when working with inconsistent or biased users, we show that deferring models still greatly improve the accuracy and/or fairness of the entire system.