NLP系统的解释性方法遇到了因果推断的基本问题的版本：对于给定的基础真相输入文本，我们从未真正观察到隔离模型表示对输出的因果影响所必需的反事实文本。作为回应，许多解释性方法不使用反事实文本，假设它们将是不可用的。在本文中，我们表明可以使用近似反事实来创建强大的因果解释方法，该方法可以由人类写成近似特定的反事实或简单地使用元数据指导的启发式启发式启示术进行采样。我们提案的核心是因果替代模型（CPM）。 CPM解释了一个黑框$ \ Mathcal {n} $，因为它经过培训可以具有与$ \ Mathcal {n} $相同的实际输入/输出行为，而创建可以介入的神经表示，以模拟反事实输入/$ \ MATHCAL {N} $的输出行为。此外，我们证明了$ \ Mathcal {n} $的最佳CPM在做出事实预测时性能与$ \ Mathcal {n} $相当地执行，这意味着CPM可以简单地替换$ \ Mathcal {n} $，从而导致更多信息可解释的部署模型。我们的代码可在https://github.com/frankaging/causal-proxy-model上找到。

众所周知，端到端的神经NLP体系结构很难理解，这引起了近年来为解释性建模的许多努力。模型解释的基本原则是忠诚，即，解释应准确地代表模型预测背后的推理过程。这项调查首先讨论了忠诚的定义和评估及其对解释性的意义。然后，我们通过将方法分为五类来介绍忠实解释的最新进展：相似性方法，模型内部结构的分析，基于反向传播的方法，反事实干预和自我解释模型。每个类别将通过其代表性研究，优势和缺点来说明。最后，我们从它们的共同美德和局限性方面讨论了上述所有方法，并反思未来的工作方向忠实的解释性。对于有兴趣研究可解释性的研究人员，这项调查将为该领域提供可访问且全面的概述，为进一步探索提供基础。对于希望更好地了解自己的模型的用户，该调查将是一项介绍性手册，帮助选择最合适的解释方法。

在许多领域，我们有很好的了解有关导致结构的洞察，这将使我们训练有素的型号有用，同时仍然可以以数据驱动的方式学习。为此，我们介绍了交换干预培训的新方法（IIT）。在IIT中，我们（1）与神经模型中的表示的因果模型中的变量和（2）列车在一个神经模型中，以匹配当两个模型中的对齐表示时的基本输入上的因果模型的反事行为它们是第二源输入的值。 IIT完全可分辨，灵活地与其他目标结合，并保证目标因果模型是当其损失最小化时神经模型的ACAUSAL抽象。我们在结构化视觉任务（MNIST-PVR）和导航指令任务（REARCAN）上评估IIT。我们将IIT与多任务培训目标和数据增强进行比较。在我们的所有实验中，IIT在他们实现目标因果模型的意义上实现了最佳结果，并产生了更可观的诠释。

Deep Learning and Machine Learning based models have become extremely popular in text processing and information retrieval. However, the non-linear structures present inside the networks make these models largely inscrutable. A significant body of research has focused on increasing the transparency of these models. This article provides a broad overview of research on the explainability and interpretability of natural language processing and information retrieval methods. More specifically, we survey approaches that have been applied to explain word embeddings, sequence modeling, attention modules, transformers, BERT, and document ranking. The concluding section suggests some possible directions for future research on this topic.

可解释的机器学习提供了有关哪些因素推动了黑盒系统的一定预测以及是否信任高风险决策或大规模部署的洞察力。现有方法主要集中于选择解释性输入功能，这些功能遵循本地添加剂或实例方法。加性模型使用启发式采样扰动来依次学习实例特定解释器。因此，该过程效率低下，并且容易受到条件较差的样品的影响。同时，实例技术直接学习本地采样分布，并可以从其他输入中利用全球信息。但是，由于严格依赖预定义的功能，他们只能解释单一级预测并在不同设置上遇到不一致的情况。这项工作利用了这两种方法的优势，并提出了一个全球框架，用于同时学习多个目标类别的本地解释。我们还提出了一种自适应推理策略，以确定特定实例的最佳功能数量。我们的模型解释器极大地超过了忠诚的添加和实例的对应物，而在各种数据集和Black-box模型体系结构上获得了高水平的简洁性。

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.

已知自然语言推断（NLI）模型从训练数据内的偏见和人工制品中学习，影响他们概括到其他看不见的数据集。现有的去偏置方法侧重于防止模型学习这些偏差，这可能导致限制模型和较低的性能。相反，我们调查教学模型如何将人类接近NLI任务，以便学习将更好地概括到以前看不见的特征。使用自然语言解释，我们监督模型的注意力，以鼓励更多地关注解释中存在的词语，显着提高模型性能。我们的实验表明，这种方法的分布式改进也伴随着分发的改进，监督模型从概括到其他NLI数据集的功能。该模型的分析表明，人类解释鼓励增加对重要词语的关注，在前提下的单词和较少关注标点符号和止扰言论的关注。

We introduce a new language representation model called BERT, which stands for Bidirectional Encoder Representations from Transformers. Unlike recent language representation models (Peters et al., 2018a;Radford et al., 2018), BERT is designed to pretrain deep bidirectional representations from unlabeled text by jointly conditioning on both left and right context in all layers. As a result, the pre-trained BERT model can be finetuned with just one additional output layer to create state-of-the-art models for a wide range of tasks, such as question answering and language inference, without substantial taskspecific architecture modifications.BERT is conceptually simple and empirically powerful. It obtains new state-of-the-art results on eleven natural language processing tasks, including pushing the GLUE score to 80.5% (7.7% point absolute improvement), MultiNLI accuracy to 86.7% (4.6% absolute improvement), SQuAD v1.1 question answering Test F1 to 93.2 (1.5 point absolute improvement) and SQuAD v2.0 Test F1 to 83.1 (5.1 point absolute improvement).

本次调查绘制了用于分析社交媒体数据的生成方法的研究状态的广泛的全景照片（Sota）。它填补了空白，因为现有的调查文章在其范围内或被约会。我们包括两个重要方面，目前正在挖掘和建模社交媒体的重要性：动态和网络。社会动态对于了解影响影响或疾病的传播，友谊的形成，友谊的形成等，另一方面，可以捕获各种复杂关系，提供额外的洞察力和识别否则将不会被注意的重要模式。

Transformer-based language models have been shown to be highly effective for several NLP tasks. In this paper, we consider three transformer models, BERT, RoBERTa, and XLNet, in both small and large version, and investigate how faithful their representations are with respect to the semantic content of texts. We formalize a notion of semantic faithfulness, in which the semantic content of a text should causally figure in a model's inferences in question answering. We then test this notion by observing a model's behavior on answering questions about a story after performing two novel semantic interventions -- deletion intervention and negation intervention. While transformer models achieve high performance on standard question answering tasks, we show that they fail to be semantically faithful once we perform these interventions for a significant number of cases (~50% for deletion intervention, and ~20% drop in accuracy for negation intervention). We then propose an intervention-based training regime that can mitigate the undesirable effects for deletion intervention by a significant margin (from ~50% to ~6%). We analyze the inner-workings of the models to better understand the effectiveness of intervention-based training for deletion intervention. But we show that this training does not attenuate other aspects of semantic unfaithfulness such as the models' inability to deal with negation intervention or to capture the predicate-argument structure of texts. We also test InstructGPT, via prompting, for its ability to handle the two interventions and to capture predicate-argument structure. While InstructGPT models do achieve very high performance on predicate-argument structure task, they fail to respond adequately to our deletion and negation interventions.

我们提出了一种可解释的关系提取方法，通过共同训练这两个目标来减轻概括和解释性之间的张力。我们的方法使用多任务学习体系结构，该体系结构共同训练分类器以进行关系提取，并在解释关系分类器的决策的关系中标记单词的序列模型。我们还将模型输出转换为规则，以将全局解释带入这种方法。使用混合策略对此序列模型进行训练：有监督，当可获得预先存在的模式的监督时，另外还要半监督。在后一种情况下，我们将序列模型的标签视为潜在变量，并学习最大化关系分类器性能的最佳分配。我们评估了两个数据集中的提议方法，并表明序列模型提供了标签，可作为关系分类器决策的准确解释，并且重要的是，联合培训通常可以改善关系分类器的性能。我们还评估了生成的规则的性能，并表明新规则是手动规则的重要附加功能，并使基于规则的系统更接近神经模型。

Language tasks involving character-level manipulations (e.g., spelling correction, many word games) are challenging for models based in subword tokenization. To address this, we adapt the interchange intervention training method of Geiger et al. (2021) to operate on type-level variables over characters. This allows us to encode robust, position-independent character-level information in the internal representations of subword-based models. We additionally introduce a suite of character-level tasks that systematically vary in their dependence on meaning and sequence-level context. While simple character-level tokenization approaches still perform best on purely form-based tasks like string reversal, our method is superior for more complex tasks that blend form, meaning, and context, such as spelling correction in context and word search games. Our approach also leads to subword-based models with human-intepretable internal representations of characters.

大型语言模型越来越能够通过相对较少的特定任务的监督产生流畅的出现文本。但这些模型可以准确解释分类决策吗？我们考虑使用少量人写的例子（即，以几滴方式）生成自由文本解释的任务。我们发现（1）创作更高质量的例子，以提示导致更高质量的世代; （2）令人惊讶的是，在头到头比较中，人群公司通常更喜欢GPT-3生成的解释，以众包中包含的人性写入的解释。然而，Crowdworker评级也表明，虽然模型产生了事实，语法和充分的解释，但它们具有改进的空间，例如沿着提供新颖信息和支持标签的轴。我们创建了一种管道，该管道将GPT-3与监督过滤器结合起来，该过滤器通过二进制可接受性判断来包含人类循环。尽管具有重要的主观性内在的判断可接受性，但我们的方法能够始终如一地过滤人类可接受的GPT-3生成的解释。

Laws and their interpretations, legal arguments and agreements\ are typically expressed in writing, leading to the production of vast corpora of legal text. Their analysis, which is at the center of legal practice, becomes increasingly elaborate as these collections grow in size. Natural language understanding (NLU) technologies can be a valuable tool to support legal practitioners in these endeavors. Their usefulness, however, largely depends on whether current state-of-the-art models can generalize across various tasks in the legal domain. To answer this currently open question, we introduce the Legal General Language Understanding Evaluation (LexGLUE) benchmark, a collection of datasets for evaluating model performance across a diverse set of legal NLU tasks in a standardized way. We also provide an evaluation and analysis of several generic and legal-oriented models demonstrating that the latter consistently offer performance improvements across multiple tasks.

Recent studies have shown the impressive efficacy of counterfactually augmented data (CAD) for reducing NLU models' reliance on spurious features and improving their generalizability. However, current methods still heavily rely on human efforts or task-specific designs to generate counterfactuals, thereby impeding CAD's applicability to a broad range of NLU tasks. In this paper, we present AutoCAD, a fully automatic and task-agnostic CAD generation framework. AutoCAD first leverages a classifier to unsupervisedly identify rationales as spans to be intervened, which disentangles spurious and causal features. Then, AutoCAD performs controllable generation enhanced by unlikelihood training to produce diverse counterfactuals. Extensive evaluations on multiple out-of-domain and challenge benchmarks demonstrate that AutoCAD consistently and significantly boosts the out-of-distribution performance of powerful pre-trained models across different NLU tasks, which is comparable or even better than previous state-of-the-art human-in-the-loop or task-specific CAD methods. The code is publicly available at https://github.com/thu-coai/AutoCAD.

虽然许多方法旨在通过突出突出特征来解释预测，但是这些解释服务的目标以及如何评估它们通常不合适。在这项工作中，我们介绍了一个框架，通过在训练教师模型的学生模型上授予学生模型的准确性增益来量化解释的价值。至关重要的是，培训期间学生可以使用解释，但在测试时间不可用。与先前的建议相比，我们的方法不太易于绘制，实现原则，自动，模型 - 无话会的归属。使用我们的框架，我们比较了许多归属方法，用于文本分类和问题应答，并观察不同学生模型架构和学习策略之间的定量差异（在中度到高度）。

最先进的文本分类器的大尺寸和复杂的决策机制使人类难以理解他们的预测，导致用户缺乏信任。这些问题导致采用Shail和集成梯度等方法来解释分类决策，通过为输入令牌分配重要性分数。然而，使用不同的随机化测试之前的工作表明，通过这些方法产生的解释可能不具有稳健性。例如，对测试集的相同预测的模型可能仍然导致不同的特征重要性排名。为了解决基于令牌的可解释性缺乏稳健性，我们探讨了句子等更高语义层面的解释。我们使用计算指标和人类主题研究来比较基于令牌的句子的解释的质量。我们的实验表明，更高级别的特征属性提供了几个优点：1）由于随机化测试测量，2）当使用近似的基于方法等诸如Shav等的方法来说，它们更加强大，并且3）它们更容易理解在语言相干性在更高的粒度水平上存在的情况下的人类。基于这些调查结果，我们表明，令牌的可解释性，同时是鉴于ML模型的输入接口的方便的首选，不是所有情况中最有效的选择。

Despite being responsible for state-of-the-art results in several computer vision and natural language processing tasks, neural networks have faced harsh criticism due to some of their current shortcomings. One of them is that neural networks are correlation machines prone to model biases within the data instead of focusing on actual useful causal relationships. This problem is particularly serious in application domains affected by aspects such as race, gender, and age. To prevent models from incurring on unfair decision-making, the AI community has concentrated efforts in correcting algorithmic biases, giving rise to the research area now widely known as fairness in AI. In this survey paper, we provide an in-depth overview of the main debiasing methods for fairness-aware neural networks in the context of vision and language research. We propose a novel taxonomy to better organize the literature on debiasing methods for fairness, and we discuss the current challenges, trends, and important future work directions for the interested researcher and practitioner.

这项调查回顾了对基于视觉的自动驾驶系统进行行为克隆训练的解释性方法。解释性的概念具有多个方面，并且需要解释性的驾驶强度是一种安全至关重要的应用。从几个研究领域收集贡献，即计算机视觉，深度学习，自动驾驶，可解释的AI（X-AI），这项调查可以解决几点。首先，它讨论了从自动驾驶系统中获得更多可解释性和解释性的定义，上下文和动机，以及该应用程序特定的挑战。其次，以事后方式为黑盒自动驾驶系统提供解释的方法是全面组织和详细的。第三，详细介绍和讨论了旨在通过设计构建更容易解释的自动驾驶系统的方法。最后，确定并检查了剩余的开放挑战和潜在的未来研究方向。

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。