Better & Faster Large Language Models via Multi-token Prediction

Large language models such as GPT and Llama are trained with a next-token prediction loss. In this work, we suggest that training language models to predict multiple future tokens at once results in higher sample efficiency. More specifically, at each position in the training corpus, we ask the model to predict the following n tokens using n independent output heads, operating on top of a shared model trunk. Considering multi-token prediction as an auxiliary training task, we measure improved downstream capabilities with no overhead in training time for both code and natural language models. The method is increasingly useful for larger model sizes, and keeps its appeal when training for multiple epochs. Gains are especially pronounced on generative benchmarks like coding, where our models consistently outperform strong baselines by several percentage points. Our 13B parameter models solves 12 % more problems on HumanEval and 17 % more on MBPP than comparable next-token models. Experiments on small algorithmic tasks demonstrate that multi-token prediction is favorable for the development of induction heads and algorithmic reasoning capabilities. As an additional benefit, models trained with 4-token prediction are up to 3 times faster at inference, even with large batch sizes.

Unified Uncertainty Calibration

To build robust, fair, and safe AI systems, we would like our classifiers to say ``I don't know'' when facing test examples that are difficult or fall outside of the training classes.The ubiquitous strategy to predict under uncertainty is the simplistic \emph{reject-or-classify} rule: abstain from prediction if epistemic uncertainty is high, classify otherwise.Unfortunately, this recipe does not allow different sources of uncertainty to communicate with each other, produces miscalibrated predictions, and it does not allow to correct for misspecifications in our uncertainty estimates. To address these three issues, we introduce \emph{unified uncertainty calibration (U2C)}, a holistic framework to combine aleatoric and epistemic uncertainties. U2C enables a clean learning-theoretical analysis of uncertainty estimation, and outperforms reject-or-classify across a variety of ImageNet benchmarks.

Discovering environments with XRM

Successful out-of-distribution generalization requires environment annotations. Unfortunately, these are resource-intensive to obtain, and their relevance to model performance is limited by the expectations and perceptual biases of human annotators. Therefore, to enable robust AI systems across applications, we must develop algorithms to automatically discover environments inducing broad generalization. Current proposals, which divide examples based on their training error, suffer from one fundamental problem. These methods add hyper-parameters and early-stopping criteria that are impossible to tune without a validation set with human-annotated environments, the very information subject to discovery. In this paper, we propose Cross-Risk-Minimization (XRM) to address this issue. XRM trains two twin networks, each learning from one random half of the training data, while imitating confident held-out mistakes made by its sibling. XRM provides a recipe for hyper-parameter tuning, does not require early-stopping, and can discover environments for all training and validation data. Domain generalization algorithms built on top of XRM environments achieve oracle worst-group-accuracy, solving a long-standing problem in out-of-distribution generalization.

Context is Environment

Two lines of work are taking the central stage in AI research. On the one hand, the community is making increasing efforts to build models that discard spurious correlations and generalize better in novel test environments. Unfortunately, the bitter lesson so far is that no proposal convincingly outperforms a simple empirical risk minimization baseline. On the other hand, large language models (LLMs) have erupted as algorithms able to learn in-context, generalizing on-the-fly to eclectic contextual circumstances that users enforce by means of prompting. In this paper, we argue that context is environment, and posit that in-context learning holds the key to better domain generalization. Via extensive theory and experiments, we show that paying attention to context$\unicode{x2013}\unicode{x2013}$unlabeled examples as they arrive$\unicode{x2013}\unicode{x2013}$allows our proposed In-Context Risk Minimization (ICRM) algorithm to zoom-in on the test environment risk minimizer, leading to significant out-of-distribution performance improvements. From all of this, two messages are worth taking home. Researchers in domain generalization should consider environment as context, and harness the adaptive power of in-context learning. Researchers in LLMs should consider context as environment, to better structure data towards generalization.

A Closer Look at In-Context Learning under Distribution Shifts

In-context learning, a capability that enables a model to learn from input examples on the fly without necessitating weight updates, is a defining characteristic of large language models. In this work, we follow the setting proposed in (Garg et al., 2022) to better understand the generality and limitations of in-context learning from the lens of the simple yet fundamental task of linear regression. The key question we aim to address is: Are transformers more adept than some natural and simpler architectures at performing in-context learning under varying distribution shifts? To compare transformers, we propose to use a simple architecture based on set-based Multi-Layer Perceptrons (MLPs). We find that both transformers and set-based MLPs exhibit in-context learning under in-distribution evaluations, but transformers more closely emulate the performance of ordinary least squares (OLS). Transformers also display better resilience to mild distribution shifts, where set-based MLPs falter. However, under severe distribution shifts, both models' in-context learning abilities diminish.

Recycling diverse models for out-of-distribution generalization

Foundation models are redefining how AI systems are built. Practitioners now follow a standard procedure to build their machine learning solutions: download a copy of a foundation model, and fine-tune it using some in-house data about the target task of interest. Consequently, the Internet is swarmed by a handful of foundation models fine-tuned on many diverse tasks. Yet, these individual fine-tunings often lack strong generalization and exist in isolation without benefiting from each other. In our opinion, this is a missed opportunity, as these specialized models contain diverse features. Based on this insight, we propose model recycling, a simple strategy that leverages multiple fine-tunings of the same foundation model on diverse auxiliary tasks, and repurposes them as rich and diverse initializations for the target task. Specifically, model recycling fine-tunes in parallel each specialized model on the target task, and then averages the weights of all target fine-tunings into a final model. Empirically, we show that model recycling maximizes model diversity by benefiting from diverse auxiliary tasks, and achieves a new state of the art on the reference DomainBed benchmark for out-of-distribution generalization. Looking forward, model recycling is a contribution to the emerging paradigm of updatable machine learning where, akin to open-source software development, the community collaborates to incrementally and reliably update machine learning models.

ImageNet-X: Understanding Model Mistakes with Factor of Variation Annotations

Deep learning vision systems are widely deployed across applications where reliability is critical. However, even today's best models can fail to recognize an object when its pose, lighting, or background varies. While existing benchmarks surface examples challenging for models, they do not explain why such mistakes arise. To address this need, we introduce ImageNet-X, a set of sixteen human annotations of factors such as pose, background, or lighting the entire ImageNet-1k validation set as well as a random subset of 12k training images. Equipped with ImageNet-X, we investigate 2,200 current recognition models and study the types of mistakes as a function of model's (1) architecture, e.g. transformer vs. convolutional, (2) learning paradigm, e.g. supervised vs. self-supervised, and (3) training procedures, e.g., data augmentation. Regardless of these choices, we find models have consistent failure modes across ImageNet-X categories. We also find that while data augmentation can improve robustness to certain factors, they induce spill-over effects to other factors. For example, strong random cropping hurts robustness on smaller objects. Together, these insights suggest to advance the robustness of modern vision models, future research should focus on collecting additional data and understanding data augmentation schemes. Along with these insights, we release a toolkit based on ImageNet-X to spur further study into the mistakes image recognition systems make.

Measuring and signing fairness as performance under multiple stakeholder distributions

As learning machines increase their influence on decisions concerning human lives, analyzing their fairness properties becomes a subject of central importance. Yet, our best tools for measuring the fairness of learning systems are rigid fairness metrics encapsulated as mathematical one-liners, offer limited power to the stakeholders involved in the prediction task, and are easy to manipulate when we exhort excessive pressure to optimize them. To advance these issues, we propose to shift focus from shaping fairness metrics to curating the distributions of examples under which these are computed. In particular, we posit that every claim about fairness should be immediately followed by the tagline "Fair under what examples, and collected by whom?". By highlighting connections to the literature in domain generalization, we propose to measure fairness as the ability of the system to generalize under multiple stress tests -- distributions of examples with social relevance. We encourage each stakeholder to curate one or multiple stress tests containing examples reflecting their (possibly conflicting) interests. The machine passes or fails each stress test by falling short of or exceeding a pre-defined metric value. The test results involve all stakeholders in a discussion about how to improve the learning system, and provide flexible assessments of fairness dependent on context and based on interpretable data. We provide full implementation guidelines for stress testing, illustrate both the benefits and shortcomings of this framework, and introduce a cryptographic scheme to enable a degree of prediction accountability from system providers.

Throwing Away Data Improves Worst-Class Error in Imbalanced Classification

Class imbalances pervade classification problems, yet their treatment differs in theory and practice. On the one hand, learning theory instructs us that \emph{more data is better}, as sample size relates inversely to the average test error over the entire data distribution. On the other hand, practitioners have long developed a plethora of tricks to improve the performance of learning machines over imbalanced data. These include data reweighting and subsampling, synthetic construction of additional samples from minority classes, ensembling expensive one-versus all architectures, and tweaking classification losses and thresholds. All of these are efforts to minimize the worst-class error, which is often associated to the minority group in the training data, and finds additional motivation in the robustness, fairness, and out-of-distribution literatures. Here we take on the challenge of developing learning theory able to describe the worst-class error of classifiers over linearly-separable data when fitted either on (i) the full training set, or (ii) a subset where the majority class is subsampled to match in size the minority class. We borrow tools from extreme value theory to show that, under distributions with certain tail properties, \emph{throwing away most data from the majority class leads to better worst-class error}.

Rich Feature Construction for the Optimization-Generalization Dilemma

There often is a dilemma between ease of optimization and robust out-of-distribution (OoD) generalization. For instance, many OoD methods rely on penalty terms whose optimization is challenging. They are either too strong to optimize reliably or too weak to achieve their goals. In order to escape this dilemma, we propose to first construct a rich representation (RFC) containing a palette of potentially useful features, ready to be used by even simple models. On the one hand, a rich representation provides a good initialization for the optimizer. On the other hand, it also provides an inductive bias that helps OoD generalization. RFC is constructed in a succession of training episodes. During each step of the discovery phase, we craft a multi-objective optimization criterion and its associated datasets in a manner that prevents the network from using the features constructed in the previous iterations. During the synthesis phase, we use knowledge distillation to force the network to simultaneously develop all the features identified during the discovery phase. RFC consistently helps six OoD methods achieve top performance on challenging invariant training benchmarks, ColoredMNIST (Arjovsky et al., 2020). Furthermore, on the realistic Camelyon17 task, our method helps both OoD and ERM methods outperform earlier compatable results by at least $5\%$, reduce standard deviation by at least $4.1\%$, and makes hyperparameter tuning and model selection more reliable.