Adapting Language Models via Token Translation

Modern large language models use a fixed tokenizer to effectively compress text drawn from a source domain. However, applying the same tokenizer to a new target domain often leads to inferior compression, more costly inference, and reduced semantic alignment. To address this deficiency, we introduce Sparse Sinkhorn Token Translation (S2T2). S2T2 trains a tailored tokenizer for the target domain and learns to translate between target and source tokens, enabling more effective reuse of the pre-trained next-source-token predictor. In our experiments with finetuned English language models, S2T2 improves both the perplexity and the compression of out-of-domain protein sequences, outperforming direct finetuning with either the source or target tokenizer. In addition, we find that token translations learned for smaller, less expensive models can be directly transferred to larger, more powerful models to reap the benefits of S2T2 at lower cost.

Virchow2: Scaling Self-Supervised Mixed Magnification Models in Pathology

Foundation models are rapidly being developed for computational pathology applications. However, it remains an open question which factors are most important for downstream performance with data scale and diversity, model size, and training algorithm all playing a role. In this work, we propose algorithmic modifications, tailored for pathology, and we present the result of scaling both data and model size, surpassing previous studies in both dimensions. We introduce two new models: Virchow2, a 632 million parameter vision transformer, and Virchow2G, a 1.9 billion parameter vision transformer, each trained with 3.1 million histopathology whole slide images, with diverse tissues, originating institutions, and stains. We achieve state of the art performance on 12 tile-level tasks, as compared to the top performing competing models. Our results suggest that data diversity and domain-specific methods can outperform models that only scale in the number of parameters, but, on average, performance benefits from the combination of domain-specific methods, data scale, and model scale.

Virchow 2: Scaling Self-Supervised Mixed Magnification Models in Pathology

Foundation models are rapidly being developed for computational pathology applications. However, it remains an open question which factors are most important for downstream performance with data scale and diversity, model size, and training algorithm all playing a role. In this work, we present the result of scaling both data and model size, surpassing previous studies in both dimensions, and introduce two new models: Virchow 2, a 632M parameter vision transformer, and Virchow 2G, a 1.85B parameter vision transformer, each trained with 3.1M histopathology whole slide images. To support this scale, we propose domain-inspired adaptations to the DINOv2 training algorithm, which is quickly becoming the default method in self-supervised learning for computational pathology. We achieve state of the art performance on twelve tile-level tasks, as compared to the top performing competing models. Our results suggest that data diversity and domain-specific training can outperform models that only scale in the number of parameters, but, on average, performance benefits from domain-tailoring, data scale, and model scale.

PRISM: A Multi-Modal Generative Foundation Model for Slide-Level Histopathology

Foundation models in computational pathology promise to unlock the development of new clinical decision support systems and models for precision medicine. However, there is a mismatch between most clinical analysis, which is defined at the level of one or more whole slide images, and foundation models to date, which process the thousands of image tiles contained in a whole slide image separately. The requirement to train a network to aggregate information across a large number of tiles in multiple whole slide images limits these models' impact. In this work, we present a slide-level foundation model for H&E-stained histopathology, PRISM, that builds on Virchow tile embeddings and leverages clinical report text for pre-training. Using the tile embeddings, PRISM produces slide-level embeddings with the ability to generate clinical reports, resulting in several modes of use. Using text prompts, PRISM achieves zero-shot cancer detection and sub-typing performance approaching and surpassing that of a supervised aggregator model. Using the slide embeddings with linear classifiers, PRISM surpasses supervised aggregator models. Furthermore, we demonstrate that fine-tuning of the PRISM slide encoder yields label-efficient training for biomarker prediction, a task that typically suffers from low availability of training data; an aggregator initialized with PRISM and trained on as little as 10% of the training data can outperform a supervised baseline that uses all of the data.

Tag-LLM: Repurposing General-Purpose LLMs for Specialized Domains

Large Language Models (LLMs) have demonstrated remarkable proficiency in understanding and generating natural language. However, their capabilities wane in highly specialized domains underrepresented in the pretraining corpus, such as physical and biomedical sciences. This work explores how to repurpose general LLMs into effective task solvers for specialized domains. We introduce a novel, model-agnostic framework for learning custom input tags, which are parameterized as continuous vectors appended to the LLM's embedding layer, to condition the LLM. We design two types of input tags: domain tags are used to delimit specialized representations (e.g., chemical formulas) and provide domain-relevant context; function tags are used to represent specific functions (e.g., predicting molecular properties) and compress function-solving instructions. We develop a three-stage protocol to learn these tags using auxiliary data and domain knowledge. By explicitly disentangling task domains from task functions, our method enables zero-shot generalization to unseen problems through diverse combinations of the input tags. It also boosts LLM's performance in various specialized domains, such as predicting protein or chemical properties and modeling drug-target interactions, outperforming expert models tailored to these tasks.

Can Generalist Foundation Models Outcompete Special-Purpose Tuning? Case Study in Medicine

Generalist foundation models such as GPT-4 have displayed surprising capabilities in a wide variety of domains and tasks. Yet, there is a prevalent assumption that they cannot match specialist capabilities of fine-tuned models. For example, most explorations to date on medical competency benchmarks have leveraged domain-specific training, as exemplified by efforts on BioGPT and Med-PaLM. We build on a prior study of GPT-4's capabilities on medical challenge benchmarks in the absence of special training. Rather than using simple prompting to highlight the model's out-of-the-box capabilities, we perform a systematic exploration of prompt engineering. We find that prompting innovation can unlock deeper specialist capabilities and show that GPT-4 easily tops prior leading results for medical benchmarks. The prompting methods we explore are general purpose, and make no specific use of domain expertise, removing the need for expert-curated content. Our experimental design carefully controls for overfitting during the prompt engineering process. We introduce Medprompt, based on a composition of several prompting strategies. With Medprompt, GPT-4 achieves state-of-the-art results on all nine of the benchmark datasets in the MultiMedQA suite. The method outperforms leading specialist models such as Med-PaLM 2 by a significant margin with an order of magnitude fewer calls to the model. Steering GPT-4 with Medprompt achieves a 27% reduction in error rate on the MedQA dataset over the best methods to date achieved with specialist models and surpasses a score of 90% for the first time. Beyond medical problems, we show the power of Medprompt to generalize to other domains and provide evidence for the broad applicability of the approach via studies of the strategy on exams in electrical engineering, machine learning, philosophy, accounting, law, nursing, and clinical psychology.

Interpretable Distribution Shift Detection using Optimal Transport

We propose a method to identify and characterize distribution shifts in classification datasets based on optimal transport. It allows the user to identify the extent to which each class is affected by the shift, and retrieves corresponding pairs of samples to provide insights on its nature. We illustrate its use on synthetic and natural shift examples. While the results we present are preliminary, we hope that this inspires future work on interpretable methods for analyzing distribution shifts.

Bayesian Optimization Over Iterative Learners with Structured Responses: A Budget-aware Planning Approach

The rising growth of deep neural networks (DNNs) and datasets in size motivates the need for efficient solutions for simultaneous model selection and training. Many methods for hyperparameter optimization (HPO) of iterative learners including DNNs attempt to solve this problem by querying and learning a response surface while searching for the optimum of that surface. However, many of these methods make myopic queries, do not consider prior knowledge about the response structure, and/or perform biased cost-aware search, all of which exacerbate identifying the best-performing model when a total cost budget is specified. This paper proposes a novel approach referred to as Budget-Aware Planning for Iterative Learners (BAPI) to solve HPO problems under a constrained cost budget. BAPI is an efficient non-myopic Bayesian optimization solution that accounts for the budget and leverages the prior knowledge about the objective function and cost function to select better configurations and to take more informed decisions during the evaluation (training). Experiments on diverse HPO benchmarks for iterative learners show that BAPI performs better than state-of-the-art baselines in most of the cases.

On Hard Episodes in Meta-Learning

Existing meta-learners primarily focus on improving the average task accuracy across multiple episodes. Different episodes, however, may vary in hardness and quality leading to a wide gap in the meta-learner's performance across episodes. Understanding this issue is particularly critical in industrial few-shot settings, where there is limited control over test episodes as they are typically uploaded by end-users. In this paper, we empirically analyse the behaviour of meta-learners on episodes of varying hardness across three standard benchmark datasets: CIFAR-FS, mini-ImageNet, and tiered-ImageNet. Surprisingly, we observe a wide gap in accuracy of around 50% between the hardest and easiest episodes across all the standard benchmarks and meta-learners. We additionally investigate various properties of hard episodes and highlight their connection to catastrophic forgetting during meta-training. To address the issue of sub-par performance on hard episodes, we investigate and benchmark different meta-training strategies based on adversarial training and curriculum learning. We find that adversarial training strategies are much more powerful than curriculum learning in improving the prediction performance on hard episodes.

Rapid Model Architecture Adaption for Meta-Learning

Network Architecture Search (NAS) methods have recently gathered much attention. They design networks with better performance and use a much shorter search time compared to traditional manual tuning. Despite their efficiency in model deployments, most NAS algorithms target a single task on a fixed hardware system. However, real-life few-shot learning environments often cover a great number of tasks (T ) and deployments on a wide variety of hardware platforms (H ). The combinatorial search complexity T times H creates a fundamental search efficiency challenge if one naively applies existing NAS methods to these scenarios. To overcome this issue, we show, for the first time, how to rapidly adapt model architectures to new tasks in a many-task many-hardware few-shot learning setup by integrating Model Agnostic Meta Learning (MAML) into the NAS flow. The proposed NAS method (H-Meta-NAS) is hardware-aware and performs optimisation in the MAML framework. H-Meta-NAS shows a Pareto dominance compared to a variety of NAS and manual baselines in popular few-shot learning benchmarks with various hardware platforms and constraints. In particular, on the 5-way 1-shot Mini-ImageNet classification task, the proposed method outperforms the best manual baseline by a large margin (5.21% in accuracy) using 60% less computation.