语言模型在需要自然语言理解的各种任务上取得了非凡的表现。然而,最先进的模型通常在需要定量推理的任务上挣扎,例如在大学一级解决数学,科学和工程问题。为了帮助缩小这一差距,我们介绍了Minerva,Minerva是一种在一般自然语言数据上鉴定的大型语言模型,并进一步培训了技术内容。该模型在不使用外部工具的情况下实现了技术基准测试的最新性能。我们还评估了我们在需要定量推理的物理学,生物学,化学,经济学和其他科学方面的200多个本科生问题上评估我们的模型,并发现该模型可以正确回答其中几乎三分之一。
translated by 谷歌翻译
许多智力努力需要解决数学问题,但这种技能仍然超出了计算机的能力。为了测量机器学习模型中的这种能力,我们介绍了数学,这是一个12,500个挑战性竞争数学问题的新数据集。数学中的每个问题都有一个完整的逐步解决方案,可用于教授模型来生成答案派生和解释。为了促进未来的研究和提高数学准确性,我们还提供了一个大型辅助预制数据集,有助于教导模型数学的基本原则。尽管我们能够提高数学准确性,但我们的结果表明,即使有巨大的变压器模型,即使有巨大的变压器模型也是相对较低的。此外,我们发现,如果缩放趋势持续,则无法增加预算和模型参数计数对于实现强大的数学推理,这将是不切实际的。虽然缩放变压器正在自动解决大多数基于文本的任务,但缩放目前没有解决数学。为了在数学问题上进行更多牵引,我们可能需要更广泛的研究界的新算法进步。
translated by 谷歌翻译
我们探索如何产生一系列思想 - 一系列中间推理步骤 - 显着提高了大语言模型执行复杂推理的能力。特别是,我们通过一种称为“思想链”提示的简单方法在足够大的语言模型中自然出现这种推理能力,在此过程中,一些思想示范被作为提示的示例提供了。三种大语模型的实验表明,促使思想链提高了一系列算术,常识和象征性推理任务的性能。经验收益可能会引人注目。例如,仅使用八个思想范围的540B参数语言模型才能在数学单词问题的GSM8K基准上实现最新的精度,甚至超过了带有验证器的Fineted GPT-3。
translated by 谷歌翻译
Large language models have recently shown promising progress in mathematical reasoning when fine-tuned with human-generated sequences walking through a sequence of solution steps. However, the solution sequences are not formally structured and the resulting model-generated sequences may not reflect the kind of systematic reasoning we might expect an expert human to produce. In this paper, we study how to build stronger reasoning capability in language models using the idea of relational abstractions. We introduce new types of sequences that more explicitly provide an abstract characterization of the transitions through intermediate solution steps to the goal state. We find that models that are supplied with such sequences as prompts can solve tasks with a significantly higher accuracy, and models that are trained to produce such sequences solve problems better than those that are trained with previously used human-generated sequences and other baselines. Our work thus takes several steps toward elucidating and improving how language models perform on tasks requiring multi-step mathematical reasoning.
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
推理是人类认知和智力的关键支柱。在过去的十年中,我们目睹了自然语言处理的巨大收益和大型语言模型的前所未有的缩放。最近的工作表征了很少射击技术的能力,例如思想链,可以在大语言模型中模仿人类的推理。这个标志性的功能很少,连同不断扩展的语言模型相结合,打开了解决各种任务的可能性的远景,例如数学单词问题,代码完成和常识性推理。促使思想链(COT)通过提供中间步骤并敦促模型遵循相同的过程,从而进一步推动了模型的性能。尽管具有令人信服的性能,但在这些模型中推理能力的起源却很少探索。这项工作启动了对大语言模型中推理机制的更深入了解的初步步骤。我们的工作围绕查询模型,同时在提示中控制除一个组件以外的所有组件外:符号,模式和文本。然后,我们分析查询之间的性能差异。我们的结果表明,在提示中存在事实模式对于COT的成功并不是必需的。尽管如此,我们从经验上表明,仅依靠模式也不足以获得高质量的结果。我们认为文本具有常识性知识和意义。我们详尽的经验分析提供了定性的例子,说明了文本和模式之间的共生关系。这种对COT的系统理解使我们能够设计简洁的思想链,被称为CCOT,在其中修剪文本和模式只能保留其关键角色,同时以PAR或更高的求解任务率交付。
translated by 谷歌翻译
虽然编程是现代社会中最广泛适用的技能之一,但现代机器学习模型仍然无法对基本问题的解决方案。尽管重要的是,对评估代码生成令人惊讶的是,很少有效,并且难以准确地评估代码生成性能。为了满足这一挑战,我们介绍了一个用于代码生成的基准。与在更受限制的设置中的事先工作不同,我们的基准测试衡量模型采取任意自然语言规范的能力,并生成满意的Python代码。类似于公司如何评估候选软件开发人员,然后我们通过检查测试用例的生成代码来评估模型。我们的基准测试包括10,000个问题,从具有简单的单线解决方案来实现实质性算法挑战。我们在GitHub和我们的培训集上微调大型语言模型,我们发现语法错误的普遍性随着模型的提高而导致呈指数级递减。最近的模型如GPT-Neo可以通过大约20%的介绍性问题的测试用例,因此我们发现机器学习模型现在开始学习如何代码。随着自动代码生成的社会意义在未来几年增加,我们的基准可以提供跟踪进步的重要措施。
translated by 谷歌翻译
我们介绍了Sparrow,这是一个寻求信息的对话代理,与提示的语言模型基线相比,训练有素,更有帮助,正确和无害。我们使用从人类反馈中的强化学习来培训我们的模型,以帮助人类评估者判断代理人的行为。首先,为了使我们的代理人更有帮助和无害,我们将良好对话的要求分解为代理人应遵循的自然语言规则,并分别向评估者询问每个规则。我们证明,这种崩溃使我们能够收集对代理行为的更多针对性的人类判断,并允许更有效的规则条件奖励模型。其次,我们的代理商在收集对模型声明的偏好判决时提供了支持事实主张的来源的证据。对于事实问题,麻雀提供的证据支持了78%的时间。比基线比基线更享受麻雀,同时对人类的对抗性探测更具弹性,在探测时只有8%的时间违反了我们的规则。最后,我们进行了广泛的分析,表明尽管我们的模型学会遵守我们的规则,但它可以表现出分布偏见。
translated by 谷歌翻译
最先进的语言模型可以在许多任务中匹配人类性能,但它们仍然努力努力执行多步数学推理。要诊断当前模型和支持研究的故障,我们介绍了GSM8K,是8.5k高质量的语言学级别学校数学词问题的数据集。我们发现即使是最大的变压器模型也无法实现高测试性能,尽管该问题分布的概念简单性。为了提高性能,我们提出培训验证者来判断模型完成的正确性。在测试时间,我们生成许多候选解决方案,并选择验证者排名最高的解决方案。我们证明,验证显着提高了GSM8K的性能,我们提供了强大的经验证据,即验证尺度更有效地具有比FineTuning基线的数据增加。
translated by 谷歌翻译
我们展示了在文本上预先培训的神经网络,并在代码上进行微调解决数学问题,通过程序合成解决了数学问题。我们将问题转化为编程任务,自动生成程序,然后从MIT的大型数学课程(单变微积分18.01,多变量计算18.02,微分方程18.03,概率和统计介绍18.05,概率和统计概要和统计概要和统计概要和统计概要和统计概要和统计概要和统计概要和统计概况概要和统计概要和统计概要和统计概率概述的大学级问题。 18.06,以及计算机科学的数学6.042)以及数学数据集的问题(在预先发生的地板,代数,计数和概率,数字理论和前进的问题上),最新数学问题的基准专门用于评估数学推理。我们探索提示生成方法,使变形金刚能够为这些主题生成问题解决程序,包括具有图的解决方案。我们在每个主题中的随机问题上生成正确的答案。我们量化了原始和转型问题之间的差距,并进行了调查以评估所产生的问题的质量和难度。这是在规模上自动解决,等级和生成大学数学课程问题的第一项工作,这代表了高等教育的里程碑。
translated by 谷歌翻译
Computational notebooks, such as Jupyter notebooks, are interactive computing environments that are ubiquitous among data scientists to perform data wrangling and analytic tasks. To measure the performance of AI pair programmers that automatically synthesize programs for those tasks given natural language (NL) intents from users, we build ARCADE, a benchmark of 1082 code generation problems using the pandas data analysis framework in data science notebooks. ARCADE features multiple rounds of NL-to-code problems from the same notebook. It requires a model to understand rich multi-modal contexts, such as existing notebook cells and their execution states as well as previous turns of interaction. To establish a strong baseline on this challenging task, we develop PaChiNCo, a 62B code language model (LM) for Python computational notebooks, which significantly outperforms public code LMs. Finally, we explore few-shot prompting strategies to elicit better code with step-by-step decomposition and NL explanation, showing the potential to improve the diversity and explainability of model predictions.
translated by 谷歌翻译
最近已被证明大型语言模型在各种任务集中获得合理的零射普通化(Brown等,2020)。它已经假设这是语言模型的隐式多任务学习的结果,在语言模型中的预押(Radford等,2019)。可以通过明确的多任务学习直接引起零拍常规化?为了以缩放测试这个问题,我们开发一个系统,以便轻松地将任何自然语言任务映射到人类可读的提示表单中。我们转换一组大量的监督数据集,每个数据集都有多个提示,具有不同的措辞。这些提示的数据集允许基准测试模型执行完全看不见的任务的能力。我们介绍了一个普拉克尔编码器 - 解码器模型(Raffel等,2020; Lester等,2021),覆盖各种任务。该模型在多个标准数据集中达到强大的零点性能,通常优于其尺寸的型号超过16倍。此外,我们的方法对来自Big-替补基准测试的任务子集具有强烈性能,优于其尺寸的6倍。所有提示和培训的型号都可以在https://github.com/ bigscience-workshop / protectsource / httpsource / https://huggingface.co/bigscience/t0pp。
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
Mathematical reasoning is a fundamental aspect of human intelligence and is applicable in various fields, including science, engineering, finance, and everyday life. The development of artificial intelligence (AI) systems capable of solving math problems and proving theorems has garnered significant interest in the fields of machine learning and natural language processing. For example, mathematics serves as a testbed for aspects of reasoning that are challenging for powerful deep learning models, driving new algorithmic and modeling advances. On the other hand, recent advances in large-scale neural language models have opened up new benchmarks and opportunities to use deep learning for mathematical reasoning. In this survey paper, we review the key tasks, datasets, and methods at the intersection of mathematical reasoning and deep learning over the past decade. We also evaluate existing benchmarks and methods, and discuss future research directions in this domain.
translated by 谷歌翻译
当前的语言模型可以产生高质量的文本。他们只是复制他们之前看到的文本,或者他们学习了普遍的语言抽象吗?要取笑这些可能性,我们介绍了乌鸦,这是一套评估生成文本的新颖性,专注于顺序结构(n-gram)和句法结构。我们将这些分析应用于四种神经语言模型(LSTM,变压器,变换器-XL和GPT-2)。对于本地结构 - 例如,单个依赖性 - 模型生成的文本比来自每个模型的测试集的人类生成文本的基线显着不那么新颖。对于大规模结构 - 例如,总句结构 - 模型生成的文本与人生成的基线一样新颖甚至更新颖,但模型仍然有时复制,在某些情况下,在训练集中重复超过1000字超过1,000字的通道。我们还表现了广泛的手动分析,表明GPT-2的新文本通常在形态学和语法中形成良好,但具有合理的语义问题(例如,是自相矛盾)。
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
Finetuning language models on a collection of datasets phrased as instructions has been shown to improve model performance and generalization to unseen tasks. In this paper we explore instruction finetuning with a particular focus on (1) scaling the number of tasks, (2) scaling the model size, and (3) finetuning on chain-of-thought data. We find that instruction finetuning with the above aspects dramatically improves performance on a variety of model classes (PaLM, T5, U-PaLM), prompting setups (zero-shot, few-shot, CoT), and evaluation benchmarks (MMLU, BBH, TyDiQA, MGSM, open-ended generation). For instance, Flan-PaLM 540B instruction-finetuned on 1.8K tasks outperforms PALM 540B by a large margin (+9.4% on average). Flan-PaLM 540B achieves state-of-the-art performance on several benchmarks, such as 75.2% on five-shot MMLU. We also publicly release Flan-T5 checkpoints, which achieve strong few-shot performance even compared to much larger models, such as PaLM 62B. Overall, instruction finetuning is a general method for improving the performance and usability of pretrained language models.
translated by 谷歌翻译
我们介绍了一种称为编程拼图的新型编程挑战,作为方案合成的客观和全面评估,并释放Python编程拼图的开源数据集(P3)。每个拼图由短Python程序$ F $定义,目标是找到一个使$ F $返回true的输入。谜题是目的,因为每个人都由其验证者$ F $的源代码完全指定,因此评估为测试候选解决方案所需的$ F $。它们不需要答案密钥或输入/输出示例,也不依赖于自然语言理解。该数据集是全面的,因为它跨越一系列困难和域的问题,从琐碎的字符串操纵问题,经典编程谜题(例如,河内塔),用于采访/竞争编程问题(例如,动态编程),在算法和数学中的长期开放问题(例如,因子)。我们开发基准枚举程序合成,GPT-3和能够解决难题的食盒求解器 - 即使没有访问任何参考解决方案 - 通过从他们自己的过去的解决方案中学习。 Codex表现最佳,解决高达18%的397个测试问题的测试问题,每次尝试和80%的问题占1,000个问题。在一个小的用户学习中,我们发现拼图解决性能和编码体验之间的正相关性,以及人类和AI求解器的难题难度之间。因此,P3的进一步改进可能对许多程序合成区域产生重大影响。
translated by 谷歌翻译
Large language models show improved downstream task performance when prompted to generate step-by-step reasoning to justify their final answers. These reasoning steps greatly improve model interpretability and verification, but objectively studying their correctness (independent of the final answer) is difficult without reliable methods for automatic evaluation. We simply do not know how often the stated reasoning steps actually support the final end task predictions. In this work, we present ROSCOE, a suite of interpretable, unsupervised automatic scores that improve and extend previous text generation evaluation metrics. To evaluate ROSCOE against baseline metrics, we design a typology of reasoning errors and collect synthetic and human evaluation scores on commonly used reasoning datasets. In contrast with existing metrics, ROSCOE can measure semantic consistency, logicality, informativeness, fluency, and factuality - among other traits - by leveraging properties of step-by-step rationales. We empirically verify the strength of our metrics on five human annotated and six programmatically perturbed diagnostics datasets - covering a diverse set of tasks that require reasoning skills and show that ROSCOE can consistently outperform baseline metrics.
translated by 谷歌翻译
Intelligently extracting and linking complex scientific information from unstructured text is a challenging endeavor particularly for those inexperienced with natural language processing. Here, we present a simple sequence-to-sequence approach to joint named entity recognition and relation extraction for complex hierarchical information in scientific text. The approach leverages a pre-trained large language model (LLM), GPT-3, that is fine-tuned on approximately 500 pairs of prompts (inputs) and completions (outputs). Information is extracted either from single sentences or across sentences in abstracts/passages, and the output can be returned as simple English sentences or a more structured format, such as a list of JSON objects. We demonstrate that LLMs trained in this way are capable of accurately extracting useful records of complex scientific knowledge for three representative tasks in materials chemistry: linking dopants with their host materials, cataloging metal-organic frameworks, and general chemistry/phase/morphology/application information extraction. This approach represents a simple, accessible, and highly-flexible route to obtaining large databases of structured knowledge extracted from unstructured text. An online demo is available at http://www.matscholar.com/info-extraction.
translated by 谷歌翻译