大型语言模型(例如GPT-3(Brown等,2020)可以执行任意任务,而无需在仅使用少数标签示例的提示之后进行微调。可以将任意任务重新构成自然语言提示,并且可以要求语言模型生成完成,并以称为基于及时的学习的范式间接执行该任务。迄今为止,主要针对单向语言模型证明了新兴迅速的学习能力。但是,预先培训的双向语言模型(例如蒙版语言建模)为转移学习提供了更强大的学习表示。这激发了促使双向模型的可能性,但是它们的预训练目标使它们与现有的提示范式不相容。我们提出SAP(顺序自动回旋提示),该技术可以使双向模型提示。利用机器翻译任务作为案例研究,我们提示了带有SAP的双向MT5模型(Xue等,2021),并演示其少量拍摄和零照片的翻译优于GPT-3等单向模型的几个单拍翻译和XGLM(Lin等,2021),尽管MT5的参数减少了约50%。我们进一步表明SAP对问题的回答和摘要有效。我们的结果首次表明基于及时的学习是更广泛的语言模型的新兴属性,而不仅仅是单向模型。
translated by 谷歌翻译
“感应头”是注意力头,它实现了一种简单的算法来完成令牌序列,例如[a] [b] ... [a] - > [b]。在这项工作中,我们提供了一个假设的初步和间接证据,即诱导头可能构成大型大型变压器模型中所有“文本学习”中大多数的机制(即减少在增加代币指数时损失的损失)。我们发现,诱导头在与秘密学习能力突然急剧上的急剧上升的位置完全相同,这是训练损失的颠簸。我们提出了六种互补的证据,认为诱导头可能是任何大小的变压器模型中一般性内部学习的机理来源。对于仅关注的小型模型,我们提供了有力的因果证据。对于具有MLP的较大模型,我们提供相关证据。
translated by 谷歌翻译
我们研究语言模型是否可以评估自己主张的有效性,并预测他们能够正确回答的问题。我们首先表明,当以正确的格式提供时,较大的模型在多样化的多项选择和True/False问题上进行了很好的校准。因此,我们可以通过要求模型首先提出答案,然后评估其答案正确的概率“ p(true)”来对开放式采样任务进行自我评估。我们发现在各种任务中,P(true)的表现,校准和缩放令人鼓舞。当我们允许模型考虑自己的许多样本之前,在预测一种特定可能性的有效性之前,自我评估的性能进一步改善。接下来,我们研究是否可以培训模型来预测“ P(ik)”,即“我知道”问题的概率,而无需参考任何特定提出的答案。模型在预测P(IK)方面表现良好,并且在跨任务中部分概括,尽管它们在新任务上的P(IK)校准方面遇到了困难。预测的p(IK)概率在存在相关的原始材料的情况下以及对数学单词问题解决方案的提示也适当增加。我们希望这些观察结果为培训更诚实的模型提供了基础,并研究了诚实对模型模仿人类写作以外的其他目标培训的案例的普遍性。
translated by 谷歌翻译
源代码存储库由大型代码库组成,通常包含容易发生的程序。软件的复杂性日益增加导致时间和识别这些缺陷的时间和成本急剧上升。存在各种方法可以自动生成错误代码的修复程序。但是,由于特定错误的可能解决方案的组合空间很大,因此没有很多工具和数据集可以有效地评估生成的代码。在这项工作中,我们介绍了FixeVal,这是一个基准,其中包括竞争性编程问题及其各自修复程序的基准。我们引入了丰富的测试套件,以评估和评估模型生成程序修复的正确性。我们将两种在编程语言上鉴定的变压器语言模型视为我们的基准,并使用基于匹配和基于执行的评估指标对其进行比较。我们的实验表明,基于匹配的指标不能准确反映模型生成的程序修复,而基于执行的方法通过专门为该解决方案设计的所有情况和场景评估程序。因此,我们认为FixeVal提供了朝着实际自动错误修复和模型生成的代码评估的步骤。
translated by 谷歌翻译
语言模型既展示了定量的改进,又展示了新的定性功能,随着规模的增加。尽管它们具有潜在的变革性影响,但这些新能力的特征却很差。为了为未来的研究提供信息,为破坏性的新模型能力做准备,并改善社会有害的效果,至关重要的是,我们必须了解目前和近乎未来的能力和语言模型的局限性。为了应对这一挑战,我们介绍了超越模仿游戏基准(Big Bench)。 Big Bench目前由204个任务组成,由132家机构的442位作者贡献。任务主题是多样的,从语言学,儿童发展,数学,常识性推理,生物学,物理学,社会偏见,软件开发等等。 Big-Bench专注于被认为超出当前语言模型的功能的任务。我们评估了OpenAI的GPT型号,Google内部密集变压器体系结构和大型基础上的开关稀疏变压器的行为,跨越了数百万到数十亿个参数。此外,一个人类专家评估者团队执行了所有任务,以提供强大的基准。研究结果包括:模型性能和校准都随规模改善,但绝对的术语(以及与评估者的性能相比);在模型类中的性能非常相似,尽管带有稀疏性。逐渐和预测的任务通常涉及大量知识或记忆成分,而在临界规模上表现出“突破性”行为的任务通常涉及多个步骤或组成部分或脆性指标;社交偏见通常会随着含糊不清的环境而随着规模而增加,但这可以通过提示来改善。
translated by 谷歌翻译
鉴于大型语言模型的广泛能力,应该有可能朝着一般的文本的助手工作,这些助手与人类价值一致,这意味着它是有帮助,诚实的和无害的。在此方向上的初始遗传,我们研究简单的基线技术和评估,例如提示。我们发现,从模型规模增加适度的干预措施的好处,概括为各种对准评估,并不会损害大型模型的性能。接下来,我们调查与对齐,比较仿制,二进制歧视和排名偏好建模相关的几个培训目标的缩放趋势。我们发现排名优先级模型比模仿学习更好地表现得多,并且通常以模型大小更有利地缩放。相比之下,二进制歧视通常与模仿学习非常类似地执行和缩放。最后,我们研究了一种“偏好模型预训练阶段的培训阶段,其目的是在对人偏好的芬明时提高样本效率。
translated by 谷歌翻译
Automatic music generation with artificial intelligence typically requires a large amount of data which is hard to obtain for many less common genres and musical instruments. To tackle this issue, we present ongoing work and preliminary findings on the possibility for deep models to transfer knowledge from language to music, by finetuning large language models pre-trained on a massive text corpus on only hundreds of MIDI files of drum performances. We show that by doing so, one of the largest, state-of-the-art models (GPT3) is capable of generating reasonable drum grooves, while models that are not pre-trained (Transformer) shows no such ability beyond naive repetition. Evaluating generated music is a challenging task, more so is evaluating drum grooves with little precedence in literature. Hence, we propose a tailored structural evaluation method and analyze drum grooves produced by GPT3 compared to those played by human professionals, exposing the strengths and weaknesses of such generation by language-to-music transfer. Our findings suggest that language-to-music transfer learning with large language models is viable and promising.
translated by 谷歌翻译
Many popular policy gradient methods for reinforcement learning follow a biased approximation of the policy gradient known as the discounted approximation. While it has been shown that the discounted approximation of the policy gradient is not the gradient of any objective function, little else is known about its convergence behavior or properties. In this paper, we show that if the discounted approximation is followed such that the discount factor is increased slowly at a rate related to a decreasing learning rate, the resulting method recovers the standard guarantees of gradient ascent on the undiscounted objective.
translated by 谷歌翻译
Traditionally, data analysis and theory have been viewed as separate disciplines, each feeding into fundamentally different types of models. Modern deep learning technology is beginning to unify these two disciplines and will produce a new class of predictively powerful space weather models that combine the physical insights gained by data and theory. We call on NASA to invest in the research and infrastructure necessary for the heliophysics' community to take advantage of these advances.
translated by 谷歌翻译
Large language models (LLMs) have demonstrated impressive capabilities in natural language understanding and generation, but the quality bar for medical and clinical applications is high. Today, attempts to assess models' clinical knowledge typically rely on automated evaluations on limited benchmarks. There is no standard to evaluate model predictions and reasoning across a breadth of tasks. To address this, we present MultiMedQA, a benchmark combining six existing open question answering datasets spanning professional medical exams, research, and consumer queries; and HealthSearchQA, a new free-response dataset of medical questions searched online. We propose a framework for human evaluation of model answers along multiple axes including factuality, precision, possible harm, and bias. In addition, we evaluate PaLM (a 540-billion parameter LLM) and its instruction-tuned variant, Flan-PaLM, on MultiMedQA. Using a combination of prompting strategies, Flan-PaLM achieves state-of-the-art accuracy on every MultiMedQA multiple-choice dataset (MedQA, MedMCQA, PubMedQA, MMLU clinical topics), including 67.6% accuracy on MedQA (US Medical License Exam questions), surpassing prior state-of-the-art by over 17%. However, human evaluation reveals key gaps in Flan-PaLM responses. To resolve this we introduce instruction prompt tuning, a parameter-efficient approach for aligning LLMs to new domains using a few exemplars. The resulting model, Med-PaLM, performs encouragingly, but remains inferior to clinicians. We show that comprehension, recall of knowledge, and medical reasoning improve with model scale and instruction prompt tuning, suggesting the potential utility of LLMs in medicine. Our human evaluations reveal important limitations of today's models, reinforcing the importance of both evaluation frameworks and method development in creating safe, helpful LLM models for clinical applications.
translated by 谷歌翻译