Large language models have achieved impressive performance on various natural language processing tasks. However, so far they have been evaluated primarily on benchmarks where all information in the input context is relevant for solving the task. In this work, we investigate the *distractibility* of large language models, i.e., how the model prediction can be distracted by irrelevant context. In particular, we introduce Grade-School Math with Irrelevant Context (GSM-IC), an arithmetic reasoning dataset with irrelevant information in the problem description. We use this benchmark to measure the distractibility of different prompting techniques for large language models, and find that the model is easily distracted by irrelevant information. We also identify several approaches for mitigating this deficiency, such as decoding with self-consistency and adding to the prompt an instruction that tells the language model to ignore the irrelevant information.

Given the recent impressive accomplishments of language models (LMs) for code generation, we explore the use of LMs as general adaptive mutation and crossover operators for an evolutionary neural architecture search (NAS) algorithm. While NAS still proves too difficult a task for LMs to succeed at solely through prompting, we find that the combination of evolutionary prompt engineering with soft prompt-tuning, a method we term EvoPrompting, consistently finds diverse and high performing models. We first demonstrate that EvoPrompting is effective on the computationally efficient MNIST-1D dataset, where EvoPrompting produces convolutional architecture variants that outperform both those designed by human experts and naive few-shot prompting in terms of accuracy and model size. We then apply our method to searching for graph neural networks on the CLRS Algorithmic Reasoning Benchmark, where EvoPrompting is able to design *novel* architectures that outperform current state-of-the-art models on 21 out of 30 algorithmic reasoning tasks while maintaining similar model size. EvoPrompting is successful at designing accurate and efficient neural network architectures across a variety of machine learning tasks, while also being general enough for easy adaptation to other tasks beyond neural network design.

Large language models (LLMs) solve problems more accurately and interpretably when instructed to work out the answer step by step using a "chain-of-thought" (CoT) prompt. One can also improve LLMs' performance on a specific task by supervised fine-tuning, i.e., by using gradient ascent on some tunable parameters to maximize the average log-likelihood of correct answers from a labeled training set. Naively combining CoT with supervised tuning requires supervision not just of the correct answers, but also of detailed rationales that lead to those answers; these rationales are expensive to produce by hand. Instead, we propose a fine-tuning strategy that tries to maximize the \emph{marginal} log-likelihood of generating a correct answer using CoT prompting, approximately averaging over all possible rationales. The core challenge is sampling from the posterior over rationales conditioned on the correct answer; we address it using a simple Markov-chain Monte Carlo (MCMC) expectation-maximization (EM) algorithm inspired by the self-taught reasoner (STaR), memoized wake-sleep, Markovian score climbing, and persistent contrastive divergence. This algorithm also admits a novel control-variate technique that drives the variance of our gradient estimates to zero as the model improves. Applying our technique to GSM8K and the tasks in BIG-Bench Hard, we find that this MCMC-EM fine-tuning technique typically improves the model's accuracy on held-out examples more than STaR or prompt-tuning with or without CoT.

Large language models have been shown to achieve remarkable performance across a variety of natural language tasks using few-shot learning, which drastically reduces the number of task-specific training examples needed to adapt the model to a particular application. To further our understanding of the impact of scale on few-shot learning, we trained a 540-billion parameter, densely activated, Transformer language model, which we call Pathways Language Model (PaLM). We trained PaLM on 6144 TPU v4 chips using Pathways, a new ML system which enables highly efficient training across multiple TPU Pods. We demonstrate continued benefits of scaling by achieving state-of-the-art few-shot learning results on hundreds of language understanding and generation benchmarks. On a number of these tasks, PaLM 540B achieves breakthrough performance, outperforming the finetuned state-of-the-art on a suite of multi-step reasoning tasks, and outperforming average human performance on the recently released BIG-bench benchmark. A significant number of BIG-bench tasks showed discontinuous improvements from model scale, meaning that performance steeply increased as we scaled to our largest model. PaLM also has strong capabilities in multilingual tasks and source code generation, which we demonstrate on a wide array of benchmarks. We additionally provide a comprehensive analysis on bias and toxicity, and study the extent of training data memorization with respect to model scale. Finally, we discuss the ethical considerations related to large language models and discuss potential mitigation strategies.

Meta-learning hyperparameter optimization (HPO) algorithms from prior experiments is a promising approach to improve optimization efficiency over objective functions from a similar distribution. However, existing methods are restricted to learning from experiments sharing the same set of hyperparameters. In this paper, we introduce the OptFormer, the first text-based Transformer HPO framework that provides a universal end-to-end interface for jointly learning policy and function prediction when trained on vast tuning data from the wild, such as Google’s Vizier database, one of the world’s largest HPO datasets. Our extensive experiments demonstrate that the OptFormer can simultaneously imitate at least 7 different HPO algorithms, which can be further improved via its function uncertainty estimates. Compared to a Gaussian Process, the OptFormer also learns a robust prior distribution for hyperparameter response functions, and can thereby provide more accurate and better calibrated predictions. This work paves the path to future extensions for training a Transformer-based model as a general HPO optimizer.

Language models have achieved remarkable performance on a wide range of tasks that require natural language understanding. Nevertheless, state-of-the-art models have generally struggled with tasks that require quantitative reasoning, such as solving mathematics, science, and engineering questions at the college level. To help close this gap, we introduce Minerva, a large language model pretrained on general natural language data and further trained on technical content. The model achieves strong performance in a variety of evaluations, including state-of-the-art performance on the MATH dataset. We also evaluate our model on over two hundred undergraduate-level problems in physics, biology, chemistry, economics, and other sciences that require quantitative reasoning, and find that the model can correctly answer nearly a quarter of them.

A key problem in program synthesis is searching over the large space of possible programs. Human programmers might decide the high-level structure of the desired program before thinking about the details; motivated by this intuition, we consider two-level search for program synthesis, in which the synthesizer first generates a plan, a sequence of symbols that describes the desired program at a high level, before generating the program. We propose to learn representations of programs that can act as plans to organize such a two-level search. Discrete latent codes are appealing for this purpose, and can be learned by applying recent work on discrete autoencoders. Based on these insights, we introduce the Latent Programmer (LP), a program synthesis method that first predicts a discrete latent code from input/output examples, and then generates the program in the target language. We evaluate the LP on two domains, demonstrating that it yields an improvement in accuracy, especially on longer programs for which search is most difficult.

Recent work demonstrated a large ensemble of convolutional neural networks (CNNs) outperforms industry-standard approaches at annotating protein sequences that are far from the training data. These results highlight the potential of deep learning to significantly advance protein sequence annotation, but this particular system is not a practical tool for many biologists because of the computational burden of making predictions using a large ensemble. In this work, we fine-tune a transformer model that is pre-trained on millions of unlabeled natural protein sequences in order to reduce the system's compute burden at prediction time and improve accuracy. By switching from a CNN to the pre-trained transformer, we lift performance from 73.6% to 90.5% using a single model on a challenging clustering-based train-test split, where the ensemble of 59 CNNs achieved 89.0%. Through extensive stratified analysis of model performance, we provide evidence that the new model's predictions are trustworthy, even in cases known to be challenging for prior methods. Finally, we provide a case study of the biological insight enabled by this approach.

The use of black-box optimization for the design of new biological sequences is an emerging research area with potentially revolutionary impact. The cost and latency of wet-lab experiments requires methods that find good sequences in few experimental rounds of large batches of sequences — a setting that off-the-shelf black-box optimization methods are ill-equipped to handle. We find that the performance of existing methods varies drastically across optimization tasks, posing a significant obstacle to real-world applications. To improve robustness, we propose Population-Based Black-Box Optimization (P3BO), which generates batches of sequences by sampling from an ensemble of methods. The number of sequences sampled from any method is proportional to the quality of sequences it previously proposed, allowing P3BO to combine the strengths of individual methods while hedging against their innate brittleness. Adapting the hyper-parameters of each of the methods online using evolutionary optimization further improves performance. Through extensive experiments on in-silico optimization tasks, we show that P3BO outperforms any single method in its population, proposing higher quality sequences as well as more diverse batches. As such, P3BO and Adaptive-P3BO are a crucial step towards deploying ML to real-world sequence design.

Bayesian optimization is a principled approach for globally optimizing expensive, black-box functions by using a surrogate model of the objective. However, each step of Bayesian optimization involves solving an inner optimization problem, in which we maximize an acquisition function derived from the surrogate model to decide where to query next. This inner problem can be challenging to solve, particularly in discrete spaces, such as protein sequences or molecular graphs, where gradient-based optimization cannot be used. Our key insight is that we can train a generative model to generate candidates that maximize the acquisition function. This is faster than standard model-free local search methods, since we can amortize the cost of learning the model across multiple rounds of Bayesian optimization. We therefore call this Amortized Bayesian Optimization. On several challenging discrete design problems, we show this method generally outperforms other methods at optimizing the inner acquisition function, resulting in more efficient optimization of the outer black-box objective.

Collecting well-annotated image datasets to train modern machine learning algorithms is prohibitively expensive for many tasks. One appealing alternative is rendering synthetic data where ground-truth annotations are generated automatically. Unfortunately, models trained purely on rendered images fail to generalize to real images. To address this shortcoming, prior work introduced unsupervised domain adaptation algorithms that have tried to either map representations between the two domains, or learn to extract features that are domain-invariant. In this work, we approach the problem in a new light by learning in an unsupervised manner a transformation in the pixel space from one domain to the other. Our generative adversarial network (GAN)-based method adapts source-domain images to appear as if drawn from the target domain. Our approach not only produces plausible samples, but also outperforms the state-of-the-art on a number of unsupervised domain adaptation scenarios by large margins. Finally, we demonstrate that the adaptation process generalizes to object classes unseen during training.

This paper investigates a method for semantic segmentation of small objects in terrestrial LIDAR scans in urban environments. The core research contribution is a hierarchical segmentation algorithm where potential merges between segments are prioritized by a learned affinity function and constrained to occur only if they achieve a significantly high object classification probability. This approach provides a way to integrate a learned shape-prior (the object classifier) into a search for the best semantic segmentation in a fast and practical algorithm. Experiments with LIDAR scans collected by Google Street View cars throughout ~100 city blocks of New York City show that the algorithm provides better segmentations and classifications than simple alternatives for cars, vans, traffic lights, and street lights.