It has been shown that NLI models are usually biased with respect to the word-overlap between premise and hypothesis; they take this feature as a primary cue for predicting the entailment label. In this paper, we focus on an overlooked aspect of the overlap bias in NLI models: the reverse word-overlap bias. Our experimental results demonstrate that current NLI models are highly biased towards the non-entailment label on instances with low overlap, and the existing debiasing methods, which are reportedly successful on existing challenge datasets, are generally ineffective in addressing this category of bias. We investigate the reasons for the emergence of the overlap bias and the role of minority examples in its mitigation. For the former, we find that the word-overlap bias does not stem from pre-training, and for the latter, we observe that in contrast to the accepted assumption, eliminating minority examples does not affect the generalizability of debiasing methods with respect to the overlap bias.

大型语言模型（LLM）已在一系列自然语言理解任务上实现了最先进的表现。但是，这些LLM可能依靠数据集偏差和文物作为预测的快捷方式。这极大地损害了他们的分布（OOD）概括和对抗性鲁棒性。在本文中，我们对最新发展的综述，这些发展解决了LLMS的鲁棒性挑战。我们首先介绍LLM的概念和鲁棒性挑战。然后，我们介绍了在LLM中识别快捷方式学习行为的方法，表征了快捷方式学习的原因以及引入缓解解决方案。最后，我们确定了关键挑战，并将这一研究线的联系引入其他方向。

The Winograd Schema Challenge (WSC) (Levesque, Davis, and Morgenstern 2011), a benchmark for commonsense reasoning, is a set of 273 expert-crafted pronoun resolution problems originally designed to be unsolvable for statistical models that rely on selectional preferences or word associations. However, recent advances in neural language models have already reached around 90% accuracy on variants of WSC. This raises an important question whether these models have truly acquired robust commonsense capabilities or whether they rely on spurious biases in the datasets that lead to an overestimation of the true capabilities of machine commonsense. To investigate this question, we introduce WINOGRANDE, a large-scale dataset of 44k problems, inspired by the original WSC design, but adjusted to improve both the scale and the hardness of the dataset. The key steps of the dataset construction consist of (1) a carefully designed crowdsourcing procedure, followed by (2) systematic bias reduction using a novel AFLITE algorithm that generalizes human-detectable word associations to machine-detectable embedding associations. The best state-of-the-art methods on WINOGRANDE achieve 59.4 -79.1%, which are ∼15-35% (absolute) below human performance of 94.0%, depending on the amount of the training data allowed (2% -100% respectively). Furthermore, we establish new state-of-the-art results on five related benchmarks -WSC (→ 90.1%), DPR (→ 93.1%), COPA(→ 90.6%), KnowRef (→ 85.6%), and Winogender (→ 97.1%). These results have dual implications: on one hand, they demonstrate the effectiveness of WINOGRANDE when used as a resource for transfer learning. On the other hand, they raise a concern that we are likely to be overestimating the true capabilities of machine commonsense across all these benchmarks. We emphasize the importance of algorithmic bias reduction in existing and future benchmarks to mitigate such overestimation.

State-of-the-art computer vision systems are trained to predict a fixed set of predetermined object categories. This restricted form of supervision limits their generality and usability since additional labeled data is needed to specify any other visual concept. Learning directly from raw text about images is a promising alternative which leverages a much broader source of supervision. We demonstrate that the simple pre-training task of predicting which caption goes with which image is an efficient and scalable way to learn SOTA image representations from scratch on a dataset of 400 million (image, text) pairs collected from the internet. After pre-training, natural language is used to reference learned visual concepts (or describe new ones) enabling zero-shot transfer of the model to downstream tasks. We study the performance of this approach by benchmarking on over 30 different existing computer vision datasets, spanning tasks such as OCR, action recognition in videos, geo-localization, and many types of fine-grained object classification. The model transfers non-trivially to most tasks and is often competitive with a fully supervised baseline without the need for any dataset specific training. For instance, we match the accuracy of the original ResNet-50 on ImageNet zero-shot without needing to use any of the 1.28 million training examples it was trained on. We release our code and pre-trained model weights at https://github.com/OpenAI/CLIP.

事实证明，对预训练的模型进行迅速基于基于预训练的模型的微调对许多自然语言处理任务有效。但是，尚未对生物医学领域的迅速进行调整。生物医学单词在一般领域通常很少见，但在生物医学环境中无处不在，这在微观调整后即使在下游生物医学应用上都显着恶化了预训练的模型的性能，尤其是在低资源场景中。我们提出了一种简单而有效的方法，可以帮助模型在迅速调整过程中学习稀有的生物医学单词。实验结果表明，我们的方法可以使用少量的香草提示设置，无需任何额外的参数或培训步骤即可提高生物医学自然推理任务6％。

Recent methods demonstrate that data augmentation using counterfactual knowledge can teach models the causal structure of a task, leading to robust and generalizable models. However, such counterfactual data often has a limited scale and diversity if crowdsourced and is computationally expensive to extend to new perturbation types if generated using supervised methods. To address this, we introduce a new framework called DISCO for automatically generating high-quality counterfactual data at scale. DISCO engineers prompts to generate phrasal perturbations with a large general language model. Then, a task-specific teacher model filters the generation to distill high-quality counterfactual data. We show that learning with this counterfactual data yields a comparatively small student model that is 6% (absolute) more robust and generalizes 5% better across distributions than baselines on various challenging evaluations. This model is also 15% more sensitive in differentiating original and counterfactual examples, on three evaluation sets written by human workers and via human-AI collaboration.

几乎没有命名的实体识别（NER）对于在有限的资源领域中标记的实体标记至关重要，因此近年来受到了适当的关注。现有的几声方法主要在域内设置下进行评估。相比之下，对于这些固有的忠实模型如何使用一些标记的域内示例在跨域NER中执行的方式知之甚少。本文提出了一种两步以理性为中心的数据增强方法，以提高模型的泛化能力。几个数据集中的结果表明，与先前的最新方法相比，我们的模型无形方法可显着提高跨域NER任务的性能，包括反事实数据增强和及时调用方法。我们的代码可在\ url {https://github.com/lifan-yuan/factmix}上获得。

最先进的上下文化模型，例如BERT使用WIC和WSD等任务，以评估其上下文表示。这本质上假设这些任务中的性能反映了模型代表耦合单词和上下文语义的程度。本研究通过在主要的语境词汇表语义任务中呈现关于在主要的上下文中的上下文交互上呈现第一定量分析（使用探测基线）来调查本假设。具体而言，基于探测基线性能，我们提出了计算数据集中的上下文或单词偏置度的措施，并在连续内绘制现有数据集。分析显示大多数现有数据集落入连续体的最终结束（即它们是严重的上下文 - 偏见或目标词偏见），而只有AM $ ^ 2 $ ICO和Sense Retrieval挑战模型代表上下文和目标词。我们对WIC的案例研究表明，人类受试者不会在数据集中共享模型的强烈情境偏见（人类发现语义判断，当目标字缺失时更加困难），并且模型正在从单独的上下文学习虚假相关性。本研究表明，通常未在这些任务中被视为在这些任务中的上下文表示的模型，因此误解误解。我们建议我们的框架作为Sanity检查的上下文和目标词偏差的未来任务设计和在词汇语义中的应用程序。

具有大量偏见的数据集当前威胁要培训有关NLU任务的值得信赖的模型。尽管取得了巨大进展，但当前的偏见方法却过分依赖偏见属性的知识。但是，属性的​​定义是难以捉摸的，并且在不同的数据集上有所不同。此外，利用输入级别的这些属性到偏置缓解可能会留下内在属性与基本决策规则之间的差距。为了缩小这一差距并解放有关偏见的监督，我们建议将缓解偏见扩展到特征空间。因此，开发了一个新型模型，即恢复具有无知识（风险）的预期功能子空间。假设由各种偏见引起的快捷键特征是为了预测而无意的，则风险将其视为冗余特征。当研究较低的歧管以去除冗余时，风险表明，具有预期功能的极低维度子空间可以牢固地表示高度偏见的数据集。经验结果表明，我们的模型可以始终如一地提高模型的概括到分布式集合，并实现新的最新性能。

The strong few-shot in-context learning capability of large pre-trained language models (PLMs) such as GPT-3 is highly appealing for application domains such as biomedicine, which feature high and diverse demands of language technologies but also high data annotation costs. In this paper, we present the first systematic and comprehensive study to compare the few-shot performance of GPT-3 in-context learning with fine-tuning smaller (i.e., BERT-sized) PLMs on two highly representative biomedical information extraction tasks, named entity recognition and relation extraction. We follow the true few-shot setting to avoid overestimating models' few-shot performance by model selection over a large validation set. We also optimize GPT-3's performance with known techniques such as contextual calibration and dynamic in-context example retrieval. However, our results show that GPT-3 still significantly underperforms compared to simply fine-tuning a smaller PLM. In addition, GPT-3 in-context learning also yields smaller gains in accuracy when more training data becomes available. Our in-depth analyses further reveal issues of the in-context learning setting that may be detrimental to information extraction tasks in general. Given the high cost of experimenting with GPT-3, we hope our study provides guidance for biomedical researchers and practitioners towards more promising directions such as fine-tuning small PLMs.

The recent GPT-3 model (Brown et al., 2020) achieves remarkable few-shot performance solely by leveraging a natural-language prompt and a few task demonstrations as input context. Inspired by their findings, we study few-shot learning in a more practical scenario, where we use smaller language models for which fine-tuning is computationally efficient. We present LM-BFF-better few-shot fine-tuning of language models 1 -a suite of simple and complementary techniques for finetuning language models on a small number of annotated examples. Our approach includes (1) prompt-based fine-tuning together with a novel pipeline for automating prompt generation; and (2) a refined strategy for dynamically and selectively incorporating demonstrations into each context. Finally, we present a systematic evaluation for analyzing few-shot performance on a range of NLP tasks, including classification and regression. Our experiments demonstrate that our methods combine to dramatically outperform standard fine-tuning procedures in this low resource setting, achieving up to 30% absolute improvement, and 11% on average across all tasks. Our approach makes minimal assumptions on task resources and domain expertise, and hence constitutes a strong task-agnostic method for few-shot learning. 2 * The first two authors contributed equally. 1 Alternatively, language models' best friends forever. 2 Our implementation is publicly available at https:// github.com/princeton-nlp/LM-BFF.

最近，与“预训练，及时和预测”的新范式相比，与“预训练，微调”范式相比，新的范式“预训练，及时和预测”取得了显着的成就。在基于及时的GPT-3成功之后，一系列基于蒙版的语言模型（MLM）（例如Bert，Roberta）及时学习方法变得流行并广泛使用。但是，另一个有效的预训练的判别模型Electra可能被忽略了。在本文中，我们尝试使用拟议的替换代替令牌检测（RTD）基于基于的及时学习方法来完成零摄像的几个NLP任务。实验结果表明，基于RTD-Prompt学习的Electra模型可达到令人惊讶的最先进的零拍性能。在数字上，与MLM-Roberta-Large和MLM-Bert-Large相比，我们的RTD-Electra-Large在所有15个任务上平均提高了约8.4％和13.7％。特别是在SST-2任务上，我们的RTD-Electra-Large在没有任何培训数据的情况下达到了令人惊讶的90.1％精度。总体而言，与预先训练的蒙版语言模型相比，预先训练的代替令牌检测模型在零拍学习中的性能更好。因此，Electra是一位出色的零球学习者。源代码可在以下网址获得：https：//github.com/nishiwen1214/rtd-electra。

Pre-trained language models (PLMs) are known to improve the generalization performance of natural language understanding models by leveraging large amounts of data during the pre-training phase. However, the out-of-distribution (OOD) generalization problem remains a challenge in many NLP tasks, limiting the real-world deployment of these methods. This paper presents the first attempt at creating a unified benchmark named GLUE-X for evaluating OOD robustness in NLP models, highlighting the importance of OOD robustness and providing insights on how to measure the robustness of a model and how to improve it. The benchmark includes 13 publicly available datasets for OOD testing, and evaluations are conducted on 8 classic NLP tasks over 19 popularly used PLMs. Our findings confirm the need for improved OOD accuracy in NLP tasks, as significant performance degradation was observed in all settings compared to in-distribution (ID) accuracy.

姿态检测的目标是确定以目标朝向目标的文本中表达的视点。这些观点或上下文通常以许多不同的语言表达，这取决于用户和平台，这可以是本地新闻插座，社交媒体平台，新闻论坛等。然而，姿态检测的大多数研究已经限于使用单一语言和几个有限的目标，在交叉舌姿态检测很少有效。此外，标记数据的非英语来源通常稀缺，并具有额外的挑战。最近，大型多语言语言模型在许多非英语任务上大大提高了性能，尤其是具有有限数量的示例。这突出了模型预培训的重要性及其从少数例子中学习的能力。在本文中，我们展示了对日期交叉姿态检测的最全面的研究：我们在6名语言系列中使用12种语言的12种不同的数据集进行实验，每个都有6个低资源评估设置。对于我们的实验，我们构建了模式开发培训，提出了添加一种新颖的标签编码器来简化言语程序。我们进一步提出了基于情绪的姿态数据进行预培训，这在与几个强的基线相比，在低拍摄环境中显示了大量的6％F1绝对的增长。

最近的自然语言理解进展（NLU）已经被驱动，部分是由胶水，超级格，小队等的基准。事实上，许多NLU模型现在在许多任务中匹配或超过“人类水平”性能这些基准。然而，大多数这些基准测试都提供模型访问相对大量的标记数据进行培训。因此，该模型提供了比人类所需的更多数据，以实现强大的性能。这有动机侧重于侧重于改善NLU模型的少量学习性能。然而，缺乏少量射门的标准化评估基准，导致不同纸张中的不同实验设置。为了帮助加速这一工作的工作，我们介绍了线索（受限制的语言理解评估标准），这是评估NLU模型的几次拍摄学习功能的基准。我们证明，虽然最近的模型在获得大量标记数据时达到人类性能，但对于大多数任务，少量拍摄设置中的性能存在巨大差距。我们还展示了几个拍摄设置中替代模型家族和适应技术之间的差异。最后，我们讨论了在设计实验设置时讨论了评估真实少量学习绩效的实验设置，并提出了统一的标准化方法，以获得少量学习评估。我们的目标是鼓励对NLU模型的研究，可以概括为具有少数示例的新任务。线索的代码和数据可以在https://github.com/microsoft/clues提供。

petroni等。 （2019）证明，可以通过将它们表达为冻结式提示并将模型的预测准确性解释为下限，作为其编码的事实信息量的较低限制，从预先接收的语言模型中检索世界事实。随后的工作已经尝试通过搜索更好的提示来缩回估计，使用不相交的事实作为培训数据。在这项工作中，我们制作两个互补贡献，以更好地了解这些事实探测技术。首先，我们提出了OptiPrompt，一种新颖的和有效的方法，直接在连续嵌入空间中优化。我们发现这种简单的方法能够预测喇嘛基准中的额外6.4％的事实。其次，我们提出了一个更重要的问题：我们真的可以将这些探测结果解释为下限吗？这些提示搜索方法是否有可能从培训数据中学习？我们发现，有些令人惊讶的是，这些方法使用的培训数据包含了潜在的事实分布的某些规则，以及所有现有的提示方法，包括我们的方法，可以利用它们以获得更好的事实预测。我们开展一系列控制实验来解除“学习”从“学习召回”，提供了更详细的图片，不同的提示可以揭示关于预先接受的语言模型。

Question answering (QA) models for reading comprehension tend to learn shortcut solutions rather than the solutions intended by QA datasets. QA models that have learned shortcut solutions can achieve human-level performance in shortcut examples where shortcuts are valid, but these same behaviors degrade generalization potential on anti-shortcut examples where shortcuts are invalid. Various methods have been proposed to mitigate this problem, but they do not fully take the characteristics of shortcuts themselves into account. We assume that the learnability of shortcuts, i.e., how easy it is to learn a shortcut, is useful to mitigate the problem. Thus, we first examine the learnability of the representative shortcuts on extractive and multiple-choice QA datasets. Behavioral tests using biased training sets reveal that shortcuts that exploit answer positions and word-label correlations are preferentially learned for extractive and multiple-choice QA, respectively. We find that the more learnable a shortcut is, the flatter and deeper the loss landscape is around the shortcut solution in the parameter space. We also find that the availability of the preferred shortcuts tends to make the task easier to perform from an information-theoretic viewpoint. Lastly, we experimentally show that the learnability of shortcuts can be utilized to construct an effective QA training set; the more learnable a shortcut is, the smaller the proportion of anti-shortcut examples required to achieve comparable performance on shortcut and anti-shortcut examples. We claim that the learnability of shortcuts should be considered when designing mitigation methods.

Conceptual knowledge is fundamental to human cognition and knowledge bases. However, existing knowledge probing works only focus on evaluating factual knowledge of pre-trained language models (PLMs) and ignore conceptual knowledge. Since conceptual knowledge often appears as implicit commonsense behind texts, designing probes for conceptual knowledge is hard. Inspired by knowledge representation schemata, we comprehensively evaluate conceptual knowledge of PLMs by designing three tasks to probe whether PLMs organize entities by conceptual similarities, learn conceptual properties, and conceptualize entities in contexts, respectively. For the tasks, we collect and annotate 24k data instances covering 393 concepts, which is COPEN, a COnceptual knowledge Probing bENchmark. Extensive experiments on different sizes and types of PLMs show that existing PLMs systematically lack conceptual knowledge and suffer from various spurious correlations. We believe this is a critical bottleneck for realizing human-like cognition in PLMs. COPEN and our codes are publicly released at https://github.com/THU-KEG/COPEN.

我们研究了掩盖语言模型（MLMS）的任务无关内在和特定于任务的外在社会偏见评估措施之间的关系，并发现这两种评估措施之间仅存在弱相关性。此外，我们发现在下游任务进行微调期间，使用不同方法的MLMS DEBIAS进行了重新划分。我们确定两个培训实例中的社会偏见及其分配的标签是内在偏见评估测量值之间差异的原因。总体而言，我们的发现突出了现有的MLM偏见评估措施的局限性，并提出了使用这些措施在下游应用程序中部署MLM的担忧。

预先训练的蒙版语言模型通过将下游任务作为文本填充来成功执行几次学习。但是，作为全镜头环境中的强大替代方案，诸如Electra之类的判别预训练模型不适合范式。在这项工作中，我们调整了基于及时的几次学习来进行电信，并表明它在广泛的任务中优于蒙面的语言模型。Electra是预先训练的，以区分令牌是产生还是原始。我们自然地将其扩展到基于迅速的几次学习，通过培训来评分目标选项的原创性，而无需引入新参数。我们的方法很容易适应涉及多token预测的任务，而无需额外的计算开销。分析表明，Electra学习分布与下游任务更好。