Naturally-occurring information-seeking questions often contain questionable assumptions -- assumptions that are false or unverifiable. Questions containing questionable assumptions are challenging because they require a distinct answer strategy that deviates from typical answers to information-seeking questions. For instance, the question "When did Marie Curie discover Uranium?" cannot be answered as a typical when question without addressing the false assumption "Marie Curie discovered Uranium". In this work, we propose (QA)$^2$ (Question Answering with Questionable Assumptions), an open-domain evaluation dataset consisting of naturally-occurring search engine queries that may or may not contain questionable assumptions. To be successful on (QA)$^2$, systems must be able to detect questionable assumptions and also be able to produce adequate responses for both typical information-seeking questions and ones with questionable assumptions. We find that current models do struggle with handling questionable assumptions -- the best performing model achieves 59% human rater acceptability on abstractive QA with (QA)$^2$ questions, leaving substantial headroom for progress.

As language models (LMs) scale, they develop many novel behaviors, good and bad, exacerbating the need to evaluate how they behave. Prior work creates evaluations with crowdwork (which is time-consuming and expensive) or existing data sources (which are not always available). Here, we automatically generate evaluations with LMs. We explore approaches with varying amounts of human effort, from instructing LMs to write yes/no questions to making complex Winogender schemas with multiple stages of LM-based generation and filtering. Crowdworkers rate the examples as highly relevant and agree with 90-100% of labels, sometimes more so than corresponding human-written datasets. We generate 154 datasets and discover new cases of inverse scaling where LMs get worse with size. Larger LMs repeat back a dialog user's preferred answer ("sycophancy") and express greater desire to pursue concerning goals like resource acquisition and goal preservation. We also find some of the first examples of inverse scaling in RL from Human Feedback (RLHF), where more RLHF makes LMs worse. For example, RLHF makes LMs express stronger political views (on gun rights and immigration) and a greater desire to avoid shut down. Overall, LM-written evaluations are high-quality and let us quickly discover many novel LM behaviors.

As AI systems become more capable, we would like to enlist their help to supervise other AIs. We experiment with methods for training a harmless AI assistant through self-improvement, without any human labels identifying harmful outputs. The only human oversight is provided through a list of rules or principles, and so we refer to the method as 'Constitutional AI'. The process involves both a supervised learning and a reinforcement learning phase. In the supervised phase we sample from an initial model, then generate self-critiques and revisions, and then finetune the original model on revised responses. In the RL phase, we sample from the finetuned model, use a model to evaluate which of the two samples is better, and then train a preference model from this dataset of AI preferences. We then train with RL using the preference model as the reward signal, i.e. we use 'RL from AI Feedback' (RLAIF). As a result we are able to train a harmless but non-evasive AI assistant that engages with harmful queries by explaining its objections to them. Both the SL and RL methods can leverage chain-of-thought style reasoning to improve the human-judged performance and transparency of AI decision making. These methods make it possible to control AI behavior more precisely and with far fewer human labels.

Developing safe and useful general-purpose AI systems will require us to make progress on scalable oversight: the problem of supervising systems that potentially outperform us on most skills relevant to the task at hand. Empirical work on this problem is not straightforward, since we do not yet have systems that broadly exceed our abilities. This paper discusses one of the major ways we think about this problem, with a focus on how to turn it into one that can be productively studied empirically. We first present an experimental design centered on choosing tasks for which human specialists succeed but unaided humans and current general AI systems fail. We then present a proof-of-concept experiment following meant to demonstrate a key feature of this experimental design and show its viability with two question-answering tasks: MMLU and time-limited QuALITY. On these tasks, we find that human participants who interact with an unreliable large-language-model dialog assistant through chat -- a trivial baseline strategy for scalable oversight -- substantially outperform both the model alone and their own unaided performance. These results are an encouraging sign that scalable oversight will be tractable to study with present models and bolster recent findings that large language models can productively assist humans with difficult tasks.

我们介绍了NLP社区Metasurvey的结果。从2022年5月到2022年6月，该调查引起了关于有争议的问题的意见，包括该领域的行业影响，对AGI和道德规范的关注。我们的结果将具体数字置于几个争议中：例如，受访者几乎完全将有关人工通用智能的重要性的问题分为一半，语言模型是否理解语言以及语言结构的必要性以及解决NLP问题的必要性。此外，调查提出了元问题，要求受访者预测调查响应的分布。这不仅使我们不仅可以深入了解NLP研究人员所拥有的各种信念，还可以揭示社区预测与现实不符的错误社会学信念。我们在各种问题上发现这种不匹配。除其他结果外，社区大大高估了其对基准的实用性的信念，以及扩展解决现实世界中问题的潜力，同时低估了其对语言结构，归纳偏见和跨学科科学重要性的信念。

自然语言处理的机器学习快速进步有可能改变有关人类学习语言的辩论。但是，当前人工学习者和人类的学习环境和偏见以削弱从学习模拟获得的证据的影响的方式分歧。例如，当今最有效的神经语言模型接受了典型儿童可用的语言数据量的大约一千倍。为了增加计算模型的可学习性结果的相关性，我们需要培训模型学习者，而没有比人类具有显着优势的学习者。如果合适的模型成功地获得了一些目标语言知识，则可以提供一个概念证明，即在假设的人类学习方案中可以学习目标。合理的模型学习者将使我们能够进行实验操作，以对学习环境中的变量进行因果推断，并严格测试史密斯风格的贫困声明，主张根据人类对人类的先天语言知识，基于有关可学习性的猜测。由于实用和道德的考虑因素，人类受试者将永远无法实现可比的实验，从而使模型学习者成为必不可少的资源。到目前为止，试图剥夺当前模型的不公平优势，为关键语法行为（例如可接受性判断）获得亚人类结果。但是，在我们可以合理地得出结论，语言学习需要比当前模型拥有更多的特定领域知识，我们必须首先以多模式刺激和多代理互动的形式探索非语言意见，以使学习者更有效地学习学习者来自有限的语言输入。

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。

为了实现长文档理解的构建和测试模型，我们引入质量，具有中文段的多项选择QA DataSet，具有约5,000个令牌的平均长度，比典型的当前模型更长。与经过段落的事先工作不同，我们的问题是由阅读整个段落的贡献者编写和验证的，而不是依赖摘要或摘录。此外，只有一半的问题是通过在紧缩时间限制下工作的注释器来应答，表明略读和简单的搜索不足以一直表现良好。目前的模型在此任务上表现不佳（55.4％），并且落后于人类性能（93.5％）。

在某些情况下，有能力的语言模型越来越饱和现有的任务基准，在某些情况下表现优于人类。这留下了很少的净空，可以衡量进一步的进步。已经提出了对抗性数据集创建作为构建更多具有挑战性的数据集的策略，以及两个常见方法是：（1）过滤易于示例和（2）循环模型数据收集。在这项工作中，我们研究了应用每种方法创造更多具有挑战性的评估数据集的影响。我们将AFLITE算法调整以筛选评估数据，并运行针对18个不同的对手模型的实验。我们发现，尽管使用更强大的对手模型，但易于选择更具挑战性的例子，降低了评估模型的性能。然而，由此产生的模型排名也可能对所用的对手模型的选择来说也是不稳定的并且非常敏感。此外，AFLITE过度的防范普普斯协议的例子，这意味着模型比较铰链在最令人争议的标记的例子上。对普遍收集的数据集ANLI和AdversarialQA的较小规模实验表明了类似的结果，在不成比例地影响对手模型的同时逐渐降低性能。

尽管与专家标签相比，众包平台通常用于收集用于培训机器学习模型的数据集，尽管标签不正确。有两种常见的策略来管理这种噪音的影响。第一个涉及汇总冗余注释，但以较少的例子为代价。其次，先前的作品还考虑使用整个注释预算来标记尽可能多的示例，然后应用Denoising算法来隐式清洁数据集。我们找到了一个中间立场，并提出了一种方法，该方法保留了一小部分注释，以明确清理高度可能的错误样本以优化注释过程。特别是，我们分配了标签预算的很大一部分，以形成用于训练模型的初始数据集。然后，该模型用于确定最有可能是不正确的特定示例，我们将剩余预算用于重新标记。在三个模型变化和四个自然语言处理任务上进行的实验表明，当分配相同的有限注释预算时，旨在处理嘈杂标签的标签聚合和高级denoising方法均优于标签聚合或匹配。