A central notion in practical and theoretical machine learning is that of a $\textit{weak learner}$, classifiers that achieve better-than-random performance (on any given distribution over data), even by a small margin. Such weak learners form the practical basis for canonical machine learning methods such as boosting. In this work, we illustrate that prompt-based large language models can operate effectively as said weak learners. Specifically, we illustrate the use of a large language model (LLM) as a weak learner in a boosting algorithm applied to tabular data. We show that by providing (properly sampled according to the distribution of interest) text descriptions of tabular data samples, LLMs can produce a summary of the samples that serves as a template for classification and achieves the aim of acting as a weak learner on this task. We incorporate these models into a boosting approach, which in some settings can leverage the knowledge within the LLM to outperform traditional tree-based boosting. The model outperforms both few-shot learning and occasionally even more involved fine-tuning procedures, particularly for tasks involving small numbers of data points. The results illustrate the potential for prompt-based LLMs to function not just as few-shot learners themselves, but as components of larger machine learning pipelines.
Deep neural language models have set new breakthroughs in many tasks of Natural Language Processing (NLP). Recent work has shown that deep transformer language models (pretrained on large amounts of texts) can achieve high levels of task-specific few-shot performance comparable to state-of-the-art models. However, the ability of these large language models in few-shot transfer learning has not yet been explored in the biomedical domain. We investigated the performance of two powerful transformer language models, i.e. GPT-3 and BioBERT, in few-shot settings on various biomedical NLP tasks. The …
Large Language Model-Driven Dynamic Assessment of Grammatical Accuracy in English Language Learner Writing
National Institute of Standards（国家标准 institute）；Department of Physics, Colorado State University（物理系，科罗拉多州立大学）；Electrical Engineering Department, University of Colorado（电气工程系，科罗拉多大学）
The goal of this work is to build flexible video-language models that can generalize to various video-to-text tasks from few examples, such as domain-specific captioning, question answering, and future event prediction. Existing few-shot video-language learners focus exclusively on the encoder, resulting in the absence of a video-to-text decoder to handle generative tasks. Video captioners have been pretrained on large-scale video-language datasets, but they rely heavily on finetuning and lack the ability to generate text for unseen tasks in a few-shot setting. We propose VidIL, a few-shot Vid…
PrivacyMind: Large Language Models Can Be Contextual Privacy Protection Learners
University of California, Los Angeles（加州大学洛杉矶分校）；Georgia Institute of Technology（佐治亚理工学院）；Tsinghua University（清华大学）；University of California, Santa Barbara（加州大学圣巴巴拉分校）；NEC Laboratories America（美国NEC实验室）
Exploring Iterative Enhancement for Improving Learnersourced Multiple-Choice Question Explanations with Large Language Models
Xtracta（埃克斯特拉克塔公司）；School of Computer Science, University of Auckland（奥克兰大学计算机科学学院）；School of Computer Science and Engineering, Sun Yat-Sen University（中山大学计算机科学与工程学院）；School of Life and Environmental Sciences, University of Sydney（悉尼大学生命与环境科学学院）
From Learner Behavior to Reusable Skills for Effective and Efficient Learner Simulation
National University of Defense Technology（国防科技大学）；Nanyang Technological University（南洋理工大学）；The Hong Kong Polytechnic University（香港理工大学）；Southeast University（东南大学）
Center for Artificial Intelligence Research (CAiRE)（人工智能研究中心）；The Hong Kong University of Science and Technology（香港科技大学）
Task-oriented dialogue systems use four connected modules, namely, Natural Language Understanding (NLU), a Dialogue State Tracking (DST), Dialogue Policy (DP) and Natural Language Generation (NLG). A research challenge is to learn each module with the least amount of samples (i.e., few-shots) given the high cost related to the data collection. The most common and effective technique to solve this problem is transfer learning, where large language models, either pre-trained on text or task-specific data, are fine-tuned on the few samples. These methods require fine-tuning steps and a set of par…
Princeton University（普林斯顿大学）；Massachusetts Institute of Technology（麻省理工学院）
The recent GPT-3 model (Brown et al., 2020) achieves remarkable few-shot performance solely by leveraging a natural-language prompt and a few task demonstrations as input context. Inspired by their findings, we study few-shot learning in a more practical scenario, where we use smaller language models for which fine-tuning is computationally efficient. We present LM-BFF--better few-shot fine-tuning of language models--a suite of simple and complementary techniques for fine-tuning language models on a small number of annotated examples. Our approach includes (1) prompt-based fine-tuning together…
University of Pennsylvania（宾夕法尼亚大学）；Microsoft（微软）；Google Research（谷歌研究院）；UNC Chapel Hill（北卡罗来纳大学教堂山分校）
Large language models such as GPT-3 (Brown et al., 2020) can perform arbitrary tasks without undergoing fine-tuning after being prompted with only a few labeled examples. An arbitrary task can be reformulated as a natural language prompt, and a language model can be asked to generate the completion, indirectly performing the task in a paradigm known as prompt-based learning. To date, emergent prompt-based learning capabilities have mainly been demonstrated for unidirectional language models. However, bidirectional language models pre-trained on denoising objectives such as masked language mode…
The classic algorithm AdaBoost allows to convert a weak learner, that is an algorithm that produces a hypothesis which is slightly better than chance, into a strong learner, achieving arbitrarily high accuracy when given enough training data. We present a new algorithm that constructs a strong learner from a weak learner but uses less training data than AdaBoost and all other weak to strong learners to achieve the same generalization bounds. A sample complexity lower bound shows that our new algorithm uses the minimum possible amount of training data and is thus optimal. Hence, this work settl…
In this paper, we predict conditional survival functions through a combined regression strategy. We take weak learners as different random survival trees. We propose to maximize concordance in the right-censored set up to find the optimal parameters. We explore two approaches, a usual survival cobra and a novel weighted predictor based on the concordance index. Our proposed formulations use two different norms, say, Max-norm and Frobenius norm, to find a proximity set of predictions from query points in the test dataset. We illustrate our algorithms through three different real-life dataset im…
When scaled to hundreds of billions of parameters, pretrained language models such as GPT-3 (Brown et al., 2020) achieve remarkable few-shot performance. However, enormous amounts of compute are required for training and applying such big models, resulting in a large carbon footprint and making it difficult for researchers and practitioners to use them. We show that performance similar to GPT-3 can be obtained with language models that are much "greener" in that their parameter count is several orders of magnitude smaller. This is achieved by converting textual inputs into cloze questions that…
Beijing Institute of Technology（北京理工大学）；NICTA（澳大利亚国家信息与通信技术研究院）；Australian National University（澳大利亚国立大学）
In this work, we propose a new optimization framework for multiclass boosting learning. In the literature, AdaBoost.MO and AdaBoost.ECC are the two successful multiclass boosting algorithms, which can use binary weak learners. We explicitly derive these two algorithms' Lagrange dual problems based on their regularized loss functions. We show that the Lagrange dual formulations enable us to design totally-corrective multiclass algorithms by using the primal-dual optimization technique. Experiments on benchmark data sets suggest that our multiclass boosting can achieve a comparable generalizatio…
Many real world learning tasks involve complex or hard-to-specify objectives, and using an easier-to-specify proxy can lead to poor performance or misaligned behavior. One solution is to have humans provide a training signal by demonstrating or judging performance, but this approach fails if the task is too complicated for a human to directly evaluate. We propose Iterated Amplification, an alternative training strategy which progressively builds up a training signal for difficult problems by combining solutions to easier subproblems. Iterated Amplification is closely related to Expert Iteratio…
Fine-tuning BERT-based models is resource-intensive in memory, computation, and time. While many prior works aim to improve inference efficiency via compression techniques, e.g., pruning, these works do not explicitly address the computational challenges of training to downstream tasks. We introduce Learner modules and priming, novel methods for fine-tuning that exploit the overparameterization of pre-trained language models to gain benefits in convergence speed and resource utilization. Learner modules navigate the double bind of 1) training efficiently by fine-tuning a subset of parameters, …
Zhejiang University（浙江大学）；Alibaba-Zhejiang University Joint Research Institute of Frontier Technologies（阿里巴巴-浙江大学前沿技术联合研究院）；Alibaba Group（阿里巴巴集团）
Large-scale pre-trained language models have contributed significantly to natural language processing by demonstrating remarkable abilities as few-shot learners. However, their effectiveness depends mainly on scaling the model parameters and prompt design, hindering their implementation in most real-world applications. This study proposes a novel pluggable, extensible, and efficient approach named DifferentiAble pRompT (DART), which can convert small language models into better few-shot learners without any prompt engineering. The main principle behind this approach involves reformulating pote…
An approach to the acceleration of parametric weak classifier boosting is proposed. Weak classifier is called parametric if it has fixed number of parameters and, so, can be represented as a point into multidimensional space. Genetic algorithm is used instead of exhaustive search to learn parameters of such classifier. Proposed approach also takes cases when effective algorithm for learning some of the classifier parameters exists into account. Experiments confirm that such an approach can dramatically decrease classifier training time while keeping both training and test errors small.
Beijing Institute of Technology（北京理工大学）；Meituan（美团）
Prompt-tuning has shown appealing performance in few-shot classification by virtue of its capability in effectively exploiting pre-trained knowledge. This motivates us to check the hypothesis that prompt-tuning is also a promising choice for long-tailed classification, since the tail classes are intuitively few-shot ones. To achieve this aim, we conduct empirical studies to examine the hypothesis. The results demonstrate that prompt-tuning makes pretrained language models at least good long-tailed learners. For intuitions on why prompt-tuning can achieve good performance in long-tailed classif…
Université de Paris（巴黎大学）；Sorbonne Université（索邦大学）；CNRS（法国国家科学研究中心）
Gradient boosting is a prediction method that iteratively combines weak learners to produce a complex and accurate model. From an optimization point of view, the learning procedure of gradient boosting mimics a gradient descent on a functional variable. This paper proposes to build upon the proximal point algorithm, when the empirical risk to minimize is not differentiable, in order to introduce a novel boosting approach, called proximal boosting. It comes with a companion algorithm inspired by [1] and called residual proximal boosting, which is aimed at better controlling the approximation er…
We consider a binary classification problem when the data comes from a mixture of two rotationally symmetric distributions satisfying concentration and anti-concentration properties enjoyed by log-concave distributions among others. We show that there exists a universal constant $C_{\mathrm{err}}>0$ such that if a pseudolabeler $\boldsymbolβ_{\mathrm{pl}}$ can achieve classification error at most $C_{\mathrm{err}}$, then for any $\varepsilon>0$, an iterative self-training algorithm initialized at $\boldsymbolβ_0 := \boldsymbolβ_{\mathrm{pl}}$ using pseudolabels $\hat y = \mathrm{sgn}(\langle \…
We study online boosting, the task of converting any weak online learner into a strong online learner. Based on a novel and natural definition of weak online learnability, we develop two online boosting algorithms. The first algorithm is an online version of boost-by-majority. By proving a matching lower bound, we show that this algorithm is essentially optimal in terms of the number of weak learners and the sample complexity needed to achieve a specified accuracy. This optimal algorithm is not adaptive however. Using tools from online loss minimization, we derive an adaptive online boosting a…
Hasso Plattner Institute（哈索·普拉特纳研究所）；University of Potsdam（波茨坦大学）
We study learners (computable devices) inferring formal languages, a setting referred to as language learning in the limit or inductive inference. In particular, we require the learners we investigate to be witness-based, that is, to justify each of their mind changes. Besides being a natural requirement for a learning task, this restriction deserves special attention as it is a specialization of various important learning paradigms. In particular, with the help of witness-based learning, explanatory learners are shown to be equally powerful under these seemingly incomparable paradigms. Noneth…
We address the general task of structured commonsense reasoning: given a natural language input, the goal is to generate a graph such as an event -- or a reasoning-graph. To employ large language models (LMs) for this task, existing approaches ``serialize'' the output graph as a flat list of nodes and edges. Although feasible, these serialized graphs strongly deviate from the natural language corpora that LMs were pre-trained on, hindering LMs from generating them correctly. In this paper, we show that when we instead frame structured commonsense reasoning tasks as code generation tasks, pre-t…
University of Amsterdam（阿姆斯特丹大学）；QuSoft（QuSoft 量子软件研究中心）；CWI（荷兰国家数学与计算机科学研究中心）
Boosting is a general method to convert a weak learner (which generates hypotheses that are just slightly better than random) into a strong learner (which generates hypotheses that are much better than random). Recently, Arunachalam and Maity gave the first quantum improvement for boosting, by combining Freund and Schapire's AdaBoost algorithm with a quantum algorithm for approximate counting. Their booster is faster than classical boosting as a function of the VC-dimension of the weak learner's hypothesis class, but worse as a function of the quality of the weak learner. In this paper we give…
