We present a robust methodology for evaluating biases in natural language generation(NLG) systems. Previous works use fixed hand-crafted prefix templates with mentions of various demographic groups to prompt models to generate continuations for bias analysis. These fixed prefix templates could themselves be specific in terms of styles or linguistic structures, which may lead to unreliable fairness conclusions that are not representative of the general trends from tone varying prompts. To study this problem, we paraphrase the prompts with different syntactic structures and use these to evaluate demographic bias in NLG systems. Our results suggest similar overall bias trends but some syntactic structures lead to contradictory conclusions compared to past works. We show that our methodology is more robust and that some syntactic structures prompt more toxic content while others could prompt less biased generation. This suggests the importance of not relying on a fixed syntactic structure and using tone-invariant prompts. Introducing syntactically-diverse prompts can achieve more robust NLG (bias) evaluation.

聊天和个人助理形式的对话系统正在越来越纳入人们的生命。现代对话系统可能会考虑采用拟人的人物，模仿社会人口统计团体对用户来说更接近和值得信赖。但是，通过一个人的通过可能导致偏见的采用。在本文中，我们向对话系统中的角色偏见提供了第一个大规模研究，并对不同社会阶层，性取向，种族和性别的人物进行分析。我们将人格偏见定义为响应的有害差异（例如，不同的冒险程度，与有害陈述的不同程度）产生从采用不同的人口统计学。此外，我们介绍了一个开源框架，UnitPersonabias，以探索对话系统中的角色偏见。通过分析搅拌机和对话对话系统，我们观察到，与不使用任何一个人的人，采用人物实际上可以减少有害响应。此外，我们发现角色选择可以影响所生成的响应中的危害程度，因此应在部署前系统地进行系统。我们还分析了角色如何导致对特定人口统计数据的不同危害。

大型语言模型会产生类似人类的文本，这些文本推动了越来越多的应用。但是，最近的文献以及越来越多的现实世界观察表明，这些模型可以产生有毒，有偏见，不真实或其他有害的语言。尽管正在进行评估语言模型危害的工作，但要远见卓识转换出可能出现的危害可能会引起严格的基准。为了促进这种翻译，我们概述了六种表征有害文本的方式，这些方法在设计新基准时值得明确考虑。然后，我们将这些特征用作镜头来识别现有基准中的趋势和差距。最后，我们将它们应用于视角API的案例研究，这是一种毒性分类器，被广泛用于HARS基准。我们的特征提供了一块桥梁，可以在远见和有效评估之间转化。

语言模型（LM）在全球许多基于语言的应用空间中变得普遍。尽管这些LMS正在改善我们与数字产品的日常互动，但无论是开放式语言还是由这些模型生成的文本仍然揭示了对特定人群的任何偏见，因此仍然存在担忧，从而冒着某种产品的可用性风险。有必要确定这些模型是否具有偏见以改善这些模型的公平性。这一差距激发了我们正在进行的工作，在该工作中，我们通过残疾镜头测量了GPT-3生成的文本的两个方面。

Generated texts from large pretrained language models have been shown to exhibit a variety of harmful, human-like biases about various demographics. These findings prompted large efforts aiming to understand and measure such effects, with the goal of providing benchmarks that can guide the development of techniques mitigating these stereotypical associations. However, as recent research has pointed out, the current benchmarks lack a robust experimental setup, consequently hindering the inference of meaningful conclusions from their evaluation metrics. In this paper, we extend these arguments and demonstrate that existing techniques and benchmarks aiming to measure stereotypes tend to be inaccurate and consist of a high degree of experimental noise that severely limits the knowledge we can gain from benchmarking language models based on them. Accordingly, we propose a new framework for robustly measuring and quantifying biases exhibited by generative language models. Finally, we use this framework to investigate GPT-3's occupational gender bias and propose prompting techniques for mitigating these biases without the need for fine-tuning.

在基于文本的分类器中测试公平性问题的一种常见方法是通过使用反事实来：如果更改输入中的敏感属性，则分类器输出是否会更改？现有的反事实生成方法通常依赖于单词列表或模板，产生不考虑语法，上下文或微妙敏感属性引用的简单反事实，并且可能会错过WordList创建者未考虑的问题。在本文中，我们介绍了一项为克服这些缺点而产生的反事实的任务，并证明了如何利用大型语言模型（LLM）来在此任务上取得进展。我们表明，这种基于LLM的方法可以产生现有方法无法实现的复杂反事实，从而比较了民事评论数据集中各种反事实生成方法的性能，并在评估毒性分类器时显示出它们的价值。

Fairness has become a trending topic in natural language processing (NLP), which addresses biases targeting certain social groups such as genders and religions. However, regional bias in language models (LMs), a long-standing global discrimination problem, still remains unexplored. This paper bridges the gap by analysing the regional bias learned by the pre-trained language models that are broadly used in NLP tasks. In addition to verifying the existence of regional bias in LMs, we find that the biases on regional groups can be strongly influenced by the geographical clustering of the groups. We accordingly propose a HiErarchical Regional Bias evaluation method (HERB) utilising the information from the sub-region clusters to quantify the bias in pre-trained LMs. Experiments show that our hierarchical metric can effectively evaluate the regional bias with respect to comprehensive topics and measure the potential regional bias that can be propagated to downstream tasks. Our codes are available at https://github.com/Bernard-Yang/HERB.

语言可以用作再现和执行有害刻板印象和偏差的手段，并被分析在许多研究中。在本文中，我们对自然语言处理中的性别偏见进行了304篇论文。我们分析了社会科学中性别及其类别的定义，并将其连接到NLP研究中性别偏见的正式定义。我们调查了在对性别偏见的研究中应用的Lexica和数据集，然后比较和对比方法来检测和减轻性别偏见。我们发现对性别偏见的研究遭受了四个核心限制。 1）大多数研究将性别视为忽视其流动性和连续性的二元变量。 2）大部分工作都在单机设置中进行英语或其他高资源语言进行。 3）尽管在NLP方法中对性别偏见进行了无数的论文，但我们发现大多数新开发的算法都没有测试他们的偏见模型，并无视他们的工作的伦理考虑。 4）最后，在这一研究线上发展的方法基本缺陷涵盖性别偏差的非常有限的定义，缺乏评估基线和管道。我们建议建议克服这些限制作为未来研究的指导。

已显示在文本上训练的NLP模型可以重现人类的刻板印象，当系统大规模部署系统时，可以放大边缘化组的危害。我们适应了Koch等人的代理 - 信号 - 局势（ABC）刻板印象模型。（2016年）从社会心理学作为系统研究和发现语言模型（LMS）中刻板印象群体特征关联的框架。我们介绍了用于测量语言模型的刻板印象关联的灵敏度测试（集合）。为了使用ABC模型评估集合和其他措施，我们从美国受试者那里收集小组特征判断，以与英语LM刻板印象进行比较。最后，我们扩展了此框架以测量相互切换身份的LM定型观念。

Recent work has presented intriguing results examining the knowledge contained in language models (LM) by having the LM fill in the blanks of prompts such as "Obama is a by profession". These prompts are usually manually created, and quite possibly suboptimal; another prompt such as "Obama worked as a " may result in more accurately predicting the correct profession. Because of this, given an inappropriate prompt, we might fail to retrieve facts that the LM does know, and thus any given prompt only provides a lower bound estimate of the knowledge contained in an LM. In this paper, we attempt to more accurately estimate the knowledge contained in LMs by automatically discovering better prompts to use in this querying process. Specifically, we propose mining-based and paraphrasing-based methods to automatically generate high-quality and diverse prompts, as well as ensemble methods to combine answers from different prompts. Extensive experiments on the LAMA benchmark for extracting relational knowledge from LMs demonstrate that our methods can improve accuracy from 31.1% to 39.6%, providing a tighter lower bound on what LMs know. We have released the code and the resulting LM Prompt And Query Archive (LPAQA) at https://github. com/jzbjyb/LPAQA.1 Some models we use in this paper, e.g. BERT (Devlin et al., 2019), are bi-directional, and do not directly define probability distribution over text, which is the underlying definition of an LM. Nonetheless, we call them LMs for simplicity.

由于细微偏见，主观性和难以在规模上获得良好质量的数据集，尤其考虑到社会偏见和社会的不断变化本质，检测文本中的社会偏见是挑战。为了解决这些挑战，我们提出了一些基于指令的基于指令的方法，以提示预先接受预先接受的语言模型（LMS）。我们从最接近查询的小型支持存储库中选择一些标签平衡的示例，以便在嵌入空间中标记。然后，我们向LM提供由标记示例的此子集的指令，查询文本被分类，偏差定义，并提示它做出决定。我们证明了几次上下文中使用的大型LMS可以检测不同类型的细粒度偏差，具有与微调模型的相似且有时卓越的精度。我们观察到，与较小模型相比，最大的530B参数模型在检测社会偏差方面明显更有效（与其他模型相比，在AUC度量上实现至少20％）。它还在几张拍摄设置中保持高AUC（掉落小于5％），其中标记的存储库减少到100个样本的少量。因此，大型预制语言模型使得更容易且更快地建立新的偏置探测器。

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.

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）。

Controllable Text Generation (CTG) is emerging area in the field of natural language generation (NLG). It is regarded as crucial for the development of advanced text generation technologies that are more natural and better meet the specific constraints in practical applications. In recent years, methods using large-scale pre-trained language models (PLMs), in particular the widely used transformer-based PLMs, have become a new paradigm of NLG, allowing generation of more diverse and fluent text. However, due to the lower level of interpretability of deep neural networks, the controllability of these methods need to be guaranteed. To this end, controllable text generation using transformer-based PLMs has become a rapidly growing yet challenging new research hotspot. A diverse range of approaches have emerged in the recent 3-4 years, targeting different CTG tasks which may require different types of controlled constraints. In this paper, we present a systematic critical review on the common tasks, main approaches and evaluation methods in this area. Finally, we discuss the challenges that the field is facing, and put forward various promising future directions. To the best of our knowledge, this is the first survey paper to summarize CTG techniques from the perspective of PLMs. We hope it can help researchers in related fields to quickly track the academic frontier, providing them with a landscape of the area and a roadmap for future research.

大型的预训练的语言模型在诸如叙事生成，问答和机器翻译等各种任务中显示出令人鼓舞的结果。同样，目前的文献趋势非常集中于控制生成的文本的显着特性，包括情感，主题和连贯性，以产生更多类似人类的输出。在这项工作中，我们引入了文本生成或UCTG的统一复杂性，这是使现有模型就所使用的输入或提示产生统一复杂文本的挑战。例如，如果输入文本提示的读数级别适用于低级学习者（CEFR中的Ex。A2），则NLG系统生成的文本也应假设此特定级别以增加可读性。在一项受控的叙事生成任务中，我们调查了160多种语言和认知动机的特征，以评估文本可读性，并发现GPT-2模型甚至人类在维护所使用的输入提示的语言复杂性方面努力。最终，我们制定了潜在的方法和方法，这些方法和方法可以将其纳入转向语言模型的一般框架中，以应对这一重要挑战。

随着人工智能系统变得越来越强大和普遍，人们对机器的道德或缺乏道德的关注变得越来越关注。然而，向机器讲授道德是一项艰巨的任务，因为道德仍然是人类中最激烈的争论问题之一，更不用说AI了。但是，部署到数百万用户的现有AI系统已经在做出充满道德影响的决策，这构成了一个看似不可能的挑战：教学机器的道德意义，而人类继续努力努力。为了探索这一挑战，我们介绍了Delphi，这是一个基于深层神经网络的实验框架，直接训练了描述性道德判断，例如，“帮助朋友”通常是不错的，而“帮助朋友传播假新闻”不是。经验结果提供了对机器伦理的承诺和局限性的新见解。面对新的道德情况，德尔菲（Delphi）表现出强大的概括能力，而现成的神经网络模型表现出明显差的判断，包括不公正的偏见，证实了对明确教学机器的道德意义的必要性。然而，德尔菲并不完美，表现出对普遍性偏见和不一致的敏感性。尽管如此，我们还是展示了不完美的Delphi的积极用例，包括在其他不完美的AI系统中将其用作组件模型。重要的是，我们根据著名的道德理论来解释Delphi的运营化，这使我们提出了重要的未来研究问题。

Several works have proven that finetuning is an applicable approach for debiasing contextualized word embeddings. Similarly, discrete prompts with semantic meanings have shown to be effective in debiasing tasks. With unfixed mathematical representation at the token level, continuous prompts usually surpass discrete ones at providing a pre-trained language model (PLM) with additional task-specific information. Despite this, relatively few efforts have been made to debias PLMs by prompt tuning with continuous prompts compared to its discrete counterpart. Furthermore, for most debiasing methods that alter a PLM's original parameters, a major problem is the need to not only decrease the bias in the PLM but also to ensure that the PLM does not lose its representation ability. Finetuning methods typically have a hard time maintaining this balance, as they tend to violently remove meanings of attribute words. In this paper, we propose ADEPT, a method to debias PLMs using prompt tuning while maintaining the delicate balance between removing biases and ensuring representation ability. To achieve this, we propose a new training criterion inspired by manifold learning and equip it with an explicit debiasing term to optimize prompt tuning. In addition, we conduct several experiments with regard to the reliability, quality, and quantity of a previously proposed attribute training corpus in order to obtain a clearer prototype of a certain attribute, which indicates the attribute's position and relative distances to other words on the manifold. We evaluate ADEPT on several widely acknowledged debiasing benchmarks and downstream tasks, and find that it achieves competitive results while maintaining (and in some cases even improving) the PLM's representation ability. We further visualize words' correlation before and after debiasing a PLM, and give some possible explanations for the visible effects.

Machine learning models are now able to convert user-written text descriptions into naturalistic images. These models are available to anyone online and are being used to generate millions of images a day. We investigate these models and find that they amplify dangerous and complex stereotypes. Moreover, we find that the amplified stereotypes are difficult to predict and not easily mitigated by users or model owners. The extent to which these image-generation models perpetuate and amplify stereotypes and their mass deployment is cause for serious concern.

文本样式传输是自然语言生成中的重要任务，旨在控制生成的文本中的某些属性，例如礼貌，情感，幽默和许多其他特性。它在自然语言处理领域拥有悠久的历史，最近由于深神经模型带来的有希望的性能而重大关注。在本文中，我们对神经文本转移的研究进行了系统调查，自2017年首次神经文本转移工作以来跨越100多个代表文章。我们讨论了任务制定，现有数据集和子任务，评估，以及丰富的方法在存在并行和非平行数据存在下。我们还提供关于这项任务未来发展的各种重要主题的讨论。我们的策据纸张列表在https://github.com/zhijing-jin/text_style_transfer_survey

我们建议一种使用大型语言模型（例如GPT-3）在给定情况下模拟不同人类的响应的方法。我们通过尝试重现公认的经济，心理语言和社会实验来测试我们的方法。该方法需要每个实验的及时模板。模拟是通过改变（假设的）主题细节（例如名称）和分析语言模型产生的文本来运行的。我们通过使用GPT-3来验证我们的方法，以表明可以模拟不同人的反应，并且他们的反应与文献中先前的人类研究一致。我们发现，较大的语言模型生成的分布与先前的实验结果更好地保持一致，这表明一种趋势，即未来的语言模型可以用于对人类反应的更忠实的模拟。我们将语言模型用于模拟的使用与对语言模型的拟人化观点形成对比。