A growing ecosystem of large, open-source foundation models has reduced the labeled data and technical expertise necessary to apply machine learning to many new problems. Yet foundation models pose a clear dual-use risk, indiscriminately reducing the costs of building both harmful and beneficial machine learning systems. To mitigate this risk, we propose the task blocking paradigm, in which foundation models are trained with an additional mechanism to impede adaptation to harmful tasks while retaining good performance on desired tasks. We call the resulting models self-destructing models, inspired by mechanisms that prevent adversaries from using tools for harmful purposes. We present an algorithm for training self-destructing models leveraging techniques from meta-learning and adversarial learning, showing that it can largely prevent a BERT-based model from learning to perform gender identification without harming the model's ability to perform profession classification. We conclude with a discussion of future directions.

Current approaches for fixing systematic problems in NLP models (e.g. regex patches, finetuning on more data) are either brittle, or labor-intensive and liable to shortcuts. In contrast, humans often provide corrections to each other through natural language. Taking inspiration from this, we explore natural language patches -- declarative statements that allow developers to provide corrective feedback at the right level of abstraction, either overriding the model (``if a review gives 2 stars, the sentiment is negative'') or providing additional information the model may lack (``if something is described as the bomb, then it is good''). We model the task of determining if a patch applies separately from the task of integrating patch information, and show that with a small amount of synthetic data, we can teach models to effectively use real patches on real data -- 1 to 7 patches improve accuracy by ~1-4 accuracy points on different slices of a sentiment analysis dataset, and F1 by 7 points on a relation extraction dataset. Finally, we show that finetuning on as many as 100 labeled examples may be needed to match the performance of a small set of language patches.

When trained on language data, do transformers learn some arbitrary computation that utilizes the full capacity of the architecture or do they learn a simpler, tree-like computation, hypothesized to underlie compositional meaning systems like human languages? There is an apparent tension between compositional accounts of human language understanding, which are based on a restricted bottom-up computational process, and the enormous success of neural models like transformers, which can route information arbitrarily between different parts of their input. One possibility is that these models, while extremely flexible in principle, in practice learn to interpret language hierarchically, ultimately building sentence representations close to those predictable by a bottom-up, tree-structured model. To evaluate this possibility, we describe an unsupervised and parameter-free method to \emph{functionally project} the behavior of any transformer into the space of tree-structured networks. Given an input sentence, we produce a binary tree that approximates the transformer's representation-building process and a score that captures how "tree-like" the transformer's behavior is on the input. While calculation of this score does not require training any additional models, it provably upper-bounds the fit between a transformer and any tree-structured approximation. Using this method, we show that transformers for three different tasks become more tree-like over the course of training, in some cases unsupervisedly recovering the same trees as supervised parsers. These trees, in turn, are predictive of model behavior, with more tree-like models generalizing better on tests of compositional generalization.

当前的口语对话系统在长时间的沉默（700-1000ms）之后开始转弯，这导致了几乎没有实时反馈，缓慢的反应和整体刻板的对话流。人类通常在200ms之内做出反应，并成功预测提前的起始点将使口语对话代理也能够做到这一点。在这项工作中，我们预测使用预先训练的语音表示模型（WAV2VEC 1.0）的韵律功能在用户音频和从预先训练的语言模型（GPT-2）上运行的单词功能（wav2Vec 1.0）的启动时间进行预测。。为了评估错误，我们提出了两个指标W.R.T.预测和真实的交货时间。我们训练和评估了总结板语料库上的模型，发现我们的方法的表现优于指标的先前工作，并且大大优于等待700ms沉默的常见方法。

我们提出了一个开放域的社交聊天机器人Chirpy Cardinal。为了既有信息又有信息，我们的机器人以一种真实的，情感上的方式与用户聊天。通过将受控的神经产生与脚手架，手写的对话整合在一起，我们让用户和机器人都轮流推动对话，从而产生引人入胜且流利的体验。Chirpy Cardinal部署在Alexa奖Socialbot Grand Challenge的第四次迭代中，每天处理数千次对话，在9个机器人中排名第二，平均用户评级为3.58/5。

大语言模型的兴起的一个关注点是它们可能造成重大伤害的潜力，尤其是在偏见，淫秽，版权和私人信息方面进行预处理。新兴的道德方法试图过滤预处理的材料，但是这种方法是临时的，未能考虑到上下文。我们提供了一种以法律为基础的过滤方法，该方法直接解决了过滤材料的权衡。首先，我们收集并提供了一堆法律，这是一个256GB（以及增长）的开源英语法律和行政数据数据集，涵盖法院意见，合同，行政规则和立法记录。对一堆法律进行预处理可能有助于解决有望改善司法接触的法律任务。其次，我们提炼政府已制定的法律规范将有毒或私人内容限制为可行的研究人员，并讨论我们的数据集如何反映这些规范。第三，我们展示了一堆法律如何为研究人员提供直接从数据中学习此类过滤规则的机会，从而为基于模型的处理提供了令人兴奋的新研究方向。

即使是最大的神经网络也会出错，随着世界的变化，曾经纠正的预测可能变得无效。模型编辑器对基础模型（预训练）模型的行为进行本地更新，以注入更新的知识或纠正不良行为。现有的模型编辑已经显示出希望，但也没有足够的表现力：他们难以准确地对编辑的预期范围进行建模（受编辑影响的示例），从而导致与编辑相关的测试输入的预测不准确，并且经常在之后完全失败。许多编辑。作为一个较高容量的替代方案，我们建议使用检索型反面模型（SERAC）提出半参数编辑，该模型（SERAC）存储在明确的内存中，并学会对它们进行推理以根据需要调节基本模型的预测。为了实现对模型编辑器的更严格评估，我们介绍了三个具有挑战性的语言模型编辑问题，基于问题回答，事实检查和对话生成。我们发现，只有SERAC才能在所有三个问题上实现高性能，从而超过了现有的方法，可以通过大量利润进行模型编辑。代码，数据和其他项目信息将在https://sites.google.com/view/serac-editing上提供。

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。

We show that large pre-trained language models are inherently highly capable of identifying label errors in natural language datasets: simply examining out-of-sample data points in descending order of fine-tuned task loss significantly outperforms more complex error-detection mechanisms proposed in previous work. To this end, we contribute a novel method for introducing realistic, human-originated label noise into existing crowdsourced datasets such as SNLI and TweetNLP. We show that this noise has similar properties to real, hand-verified label errors, and is harder to detect than existing synthetic noise, creating challenges for model robustness. We argue that human-originated noise is a better standard for evaluation than synthetic noise. Finally, we use crowdsourced verification to evaluate the detection of real errors on IMDB, Amazon Reviews, and Recon, and confirm that pre-trained models perform at a 9-36% higher absolute Area Under the Precision-Recall Curve than existing models.

最近的开放式域问题的作品应答使用检索器模型引用外部知识库，可选地重新映射与单独的重新编制模型，并使用另一个读取器模型生成答案。尽管执行相关任务，但模型具有单独的参数，并且在训练期间略微耦合。在这项工作中，我们建议将猎犬和重新划分为依次应用于变压器架构内的硬注视机制，并将所产生的计算表示给读者送入。在这个奇异模型架构中，隐藏的表示从搬运者逐渐改进到Reranker到读者，这更有效地利用模型容量，并且当我们以端到端的方式训练时，还导致更好的梯度流动。我们还提出了一种预先训练的方法，以有效地培训这种架构。我们评估我们的自然问题和TriviaQA Open DataSets的模型以及固定参数预算，我们的模型优于以前的最先进模型1.0和0.7精确匹配分数。