比较基准数据集的模型性能是人工智能测量和驱动进展的一个组成部分。模型在基准数据集上的性能通常基于单个或一小组性能指标进行评估。虽然这使得能够快速比较，但如果度量标准不充分覆盖所有性能特征，则可能导致模型性能不充分反映模型性能。它在多大程度上可能影响基准努力。为了解决这个问题，我们根据数据涵盖了3867个机器学习模型性能的基于数据，分析了当前的性能指标景观，从而用代码的开放存储库的“论文”。我们的研究结果表明，目前使用的大多数指标都有可能导致模型绩效反映不足的属性。虽然已经提出了解决有问题属性的替代度量，但目前很少使用它们。此外，我们描述了报告的指标中的歧义，这可能导致难以解释和比较模型表演。

Natural Language Generation (NLG) has improved exponentially in recent years thanks to the development of sequence-to-sequence deep learning technologies such as Transformer-based language models. This advancement has led to more fluent and coherent NLG, leading to improved development in downstream tasks such as abstractive summarization, dialogue generation and data-to-text generation. However, it is also apparent that deep learning based generation is prone to hallucinate unintended text, which degrades the system performance and fails to meet user expectations in many real-world scenarios. To address this issue, many studies have been presented in measuring and mitigating hallucinated texts, but these have never been reviewed in a comprehensive manner before. In this survey, we thus provide a broad overview of the research progress and challenges in the hallucination problem in NLG. The survey is organized into two parts: (1) a general overview of metrics, mitigation methods, and future directions; and (2) an overview of task-specific research progress on hallucinations in the following downstream tasks, namely abstractive summarization, dialogue generation, generative question answering, data-to-text generation, machine translation, and visual-language generation. This survey serves to facilitate collaborative efforts among researchers in tackling the challenge of hallucinated texts in NLG.

学术研究是解决以前从未解决过的问题的探索活动。通过这种性质，每个学术研究工作都需要进行文献审查，以区分其Novelties尚未通过事先作品解决。在自然语言处理中，该文献综述通常在“相关工作”部分下进行。鉴于研究文件的其余部分和引用的论文列表，自动相关工作生成的任务旨在自动生成“相关工作”部分。虽然这项任务是在10年前提出的，但直到最近，它被认为是作为科学多文件摘要问题的变种。然而，即使在今天，尚未标准化了自动相关工作和引用文本生成的问题。在这项调查中，我们进行了一个元研究，从问题制定，数据集收集，方法方法，绩效评估和未来前景的角度来比较相关工作的现有文献，以便为读者洞察到国家的进步 - 最内容的研究，以及如何进行未来的研究。我们还调查了我们建议未来工作要考虑整合的相关研究领域。

根据研究人员在歧视和校准性能方面采用的标准评估实践，这项工作旨在了解阶级不平衡对胸部X射线分类器的性能的影响。首先，我们进行了一项文献研究，分析了普通科学实践并确认：（1）即使在处理高度不平衡的数据集时，社区也倾向于使用由大多数阶级主导的指标; （2）包括包括胸部X射线分类器的校准研究仍然罕见，尽管其在医疗保健的背景下的重要性。其次，我们对两个主要胸部X射线数据集进行了系统实验，探讨了不同类别比率下的几种性能指标的行为，并显示了广泛采用的指标可以隐藏少数阶级中的性能。最后，我们提出了通过两个替代度量，精密召回曲线和平衡的Brier得分，这更好地反映了系统在这种情况下的性能。我们的研究结果表明，胸部X射线分类器研究界采用的当前评估实践可能无法反映真实临床情景中计算机辅助诊断系统的性能，并建议改善这种情况的替代方案。

We propose BERTSCORE, an automatic evaluation metric for text generation. Analogously to common metrics, BERTSCORE computes a similarity score for each token in the candidate sentence with each token in the reference sentence. However, instead of exact matches, we compute token similarity using contextual embeddings. We evaluate using the outputs of 363 machine translation and image captioning systems. BERTSCORE correlates better with human judgments and provides stronger model selection performance than existing metrics. Finally, we use an adversarial paraphrase detection task to show that BERTSCORE is more robust to challenging examples when compared to existing metrics.

诸如学术文章和商业报告之类的长期文件一直是详细说明重要问题和需要额外关注的复杂主题的标准格式。自动汇总系统可以有效地将长文档置于简短而简洁的文本中，以封装最重要的信息，从而在帮助读者的理解中很重要。最近，随着神经体系结构的出现，已经做出了重大的研究工作，以推动自动文本摘要系统，以及有关将这些系统扩展到长期文档领域的挑战的大量研究。在这项调查中，我们提供了有关长期文档摘要的研究的全面概述，以及其研究环境的三个主要组成部分的系统评估：基准数据集，汇总模型和评估指标。对于每个组成部分，我们在长期汇总的背景下组织文献，并进行经验分析，以扩大有关当前研究进度的观点。实证分析包括一项研究基准数据集的内在特征，摘要模型的多维分析以及摘要评估指标的综述。根据总体发现，我们通过提出可能在这个快速增长的领域中提出未来探索的方向来得出结论。

文本生成的广泛使用的评估指标要么与更长的文本效果不错，要么无法评估文本质量的所有方面。在本文中，我们引入了一个名为SMART的新指标，以减轻此类限制。具体而言，我们将句子视为匹配的基本单位，而不是代币，并使用句子匹配函数来匹配匹配候选和参考句子。还将候选句子与源文件中的句子进行了比较，以允许接地（例如，事实）评估。我们的结果表明，我们提出的指标与基于模型的匹配函数的系统级相关性优于萨姆瓦尔摘要元评估数据集上的所有竞争指标指标。后者不使用任何神经模型，这在模型开发阶段很有用，在这些阶段，资源可以受到限制且需要快速评估。最后，我们还进行了广泛的分析，表明我们提出的指标与较长的摘要很好地运行，并且对特定模型的偏见较小。

Human evaluation is the foundation upon which the evaluation of both summarization systems and automatic metrics rests. However, existing human evaluation protocols and benchmarks for summarization either exhibit low inter-annotator agreement or lack the scale needed to draw statistically significant conclusions, and an in-depth analysis of human evaluation is lacking. In this work, we address the shortcomings of existing summarization evaluation along the following axes: 1) We propose a modified summarization salience protocol, Atomic Content Units (ACUs), which relies on fine-grained semantic units and allows for high inter-annotator agreement. 2) We curate the Robust Summarization Evaluation (RoSE) benchmark, a large human evaluation dataset consisting of over 22k summary-level annotations over state-of-the-art systems on three datasets. 3) We compare our ACU protocol with three other human evaluation protocols, underscoring potential confounding factors in evaluation setups. 4) We evaluate existing automatic metrics using the collected human annotations across evaluation protocols and demonstrate how our benchmark leads to more statistically stable and significant results. Furthermore, our findings have important implications for evaluating large language models (LLMs), as we show that LLMs adjusted by human feedback (e.g., GPT-3.5) may overfit unconstrained human evaluation, which is affected by the annotators' prior, input-agnostic preferences, calling for more robust, targeted evaluation methods.

As machine translation (MT) metrics improve their correlation with human judgement every year, it is crucial to understand the limitations of such metrics at the segment level. Specifically, it is important to investigate metric behaviour when facing accuracy errors in MT because these can have dangerous consequences in certain contexts (e.g., legal, medical). We curate ACES, a translation accuracy challenge set, consisting of 68 phenomena ranging from simple perturbations at the word/character level to more complex errors based on discourse and real-world knowledge. We use ACES to evaluate a wide range of MT metrics including the submissions to the WMT 2022 metrics shared task and perform several analyses leading to general recommendations for metric developers. We recommend: a) combining metrics with different strengths, b) developing metrics that give more weight to the source and less to surface-level overlap with the reference and c) explicitly modelling additional language-specific information beyond what is available via multilingual embeddings.

基准测试对于人工智能（AI）的衡量和转向进步至关重要。但是，最近的研究引起了人们对AI基准测试状态的关注，报告了基准过度拟合，基准测试饱和度以及基准数据集创建的集中化等问题。为了促进监测AI基准测试生态系统的健康状况，我们介绍了创建基准创建和饱和全球动力学的凝结图的方法。我们策划了1688个基准测试的数据，涵盖了计算机视觉和自然语言处理的整个领域，并表明很大一部分基准迅速趋向于近乎饱和，许多基准无法找到广泛的利用，并且基准为不同AI的基准性能增长任务容易出现不可预见的爆发。我们分析与基准流行相关的属性，并得出结论，未来的基准应该强调多功能性，广度和现实世界实用程序。

尽管自动图像分析的重要性不断增加，但最近的元研究揭示了有关算法验证的主要缺陷。性能指标对于使用的自动算法的有意义，客观和透明的性能评估和验证尤其是关键，但是在使用特定的指标进行给定的图像分析任务时，对实际陷阱的关注相对较少。这些通常与（1）无视固有的度量属性，例如在存在类不平衡或小目标结构的情况下的行为，（2）无视固有的数据集属性，例如测试的非独立性案例和（3）无视指标应反映的实际生物医学领域的兴趣。该动态文档的目的是说明图像分析领域通常应用的性能指标的重要局限性。在这种情况下，它重点介绍了可以用作图像级分类，语义分割，实例分割或对象检测任务的生物医学图像分析问题。当前版本是基于由全球60多家机构的国际图像分析专家进行的关于指标的Delphi流程。

近年来，研究人员创建并引入了大量各种代码生成模型。由于对每个新模型版本的人类评估都是不可行的，因此社区采用了自动评估指标，例如BLEU来近似人类判断的结果。这些指标源自机器翻译域，目前尚不清楚它们是否适用于代码生成任务，以及他们与人类对此任务的评估有多一致。还有两个指标，即Codebleu和Ruby，它们是为了估计代码的相似性并考虑了代码属性的。但是，对于这些指标，几乎没有关于他们与人类评估一致的研究。尽管如此，公制得分的最小差异仍用于声称某些代码生成模型的优越性。在本文中，我们介绍了一项有关六个指标的适用性的研究-Bleu，Rouge-L，Meteor，Chrf，Codebleu，Ruby-用于评估代码生成模型。我们对两个不同的代码生成数据集进行了一项研究，并使用人类注释来评估这些数据集上运行的所有模型的质量。结果表明，对于Python单线的Conala数据集，如果模型得分的差异小于5分，则没有一个指标可以正确模拟人类判断，而$ 95 \％$确定性，则使用$> 95 \％$确定性。对于由特定结构类别组成的炉石传说数据集，至少2分的模型得分差异足以声称一种模型比另一个模型的优越性。使用我们的发现，我们得出了有关使用指标来估计代码生成任务的模型性能的几项建议。

Grammatical Error Correction (GEC) is the task of automatically detecting and correcting errors in text. The task not only includes the correction of grammatical errors, such as missing prepositions and mismatched subject-verb agreement, but also orthographic and semantic errors, such as misspellings and word choice errors respectively. The field has seen significant progress in the last decade, motivated in part by a series of five shared tasks, which drove the development of rule-based methods, statistical classifiers, statistical machine translation, and finally neural machine translation systems which represent the current dominant state of the art. In this survey paper, we condense the field into a single article and first outline some of the linguistic challenges of the task, introduce the most popular datasets that are available to researchers (for both English and other languages), and summarise the various methods and techniques that have been developed with a particular focus on artificial error generation. We next describe the many different approaches to evaluation as well as concerns surrounding metric reliability, especially in relation to subjective human judgements, before concluding with an overview of recent progress and suggestions for future work and remaining challenges. We hope that this survey will serve as comprehensive resource for researchers who are new to the field or who want to be kept apprised of recent developments.

多文件摘要（MDS）是信息聚合的有效工具，它从与主题相关文档集群生成信息和简洁的摘要。我们的调查是，首先，系统地概述了最近的基于深度学习的MDS模型。我们提出了一种新的分类学，总结神经网络的设计策略，并进行全面的最先进的概要。我们突出了在现有文献中很少讨论的各种客观函数之间的差异。最后，我们提出了与这个新的和令人兴奋的领域有关的几个方向。

在本文中，我们将科学文章分类为自然语言处理（NLP）和机器学习（ML）的科学文章（i）是否通过引入击败现有模型或的新型技术来扩展当前的最新技术是否（ii）他们是否主要批评现有的最新技术，即，它相对于某些属性（例如，错误的评估，错误的数据集，误导性的任务规范）不足。我们将（i）下的贡献称为具有\ enquote {正姿势}和（ii）下的贡献为具有\ enquote {负姿势}（对相关工作）。我们注释来自NLP和ML的1.5k纸以超过1.5k的论文来培训基于SCIBERT的模型，以自动根据其标题和抽象来预测论文的立场。然后，我们分析了NLP和ML的最后35年$ 35年以上的41k纸上的大规模趋势，发现随着时间的流逝，论文变得更加积极，但是负面论文也变得更加负面，我们观察到更多的负面论文，我们观察到了更多的负面论文。最近几年。在收到的引用方面，负面论文也更具影响力。

自然语言处理研究人员已经确定了对生成任务的评估方法的局限性，具有新的问题，提出了自动指标和人群判断的有效性。同时，改善生成模型的努力倾向于专注于简单的n-gram重叠度量（例如，Bleu，Rouge）。我们认为，对模型和指标的新进展应该每个人都更直接受益并告知另一个。因此，我们提出了排行榜，竞争排行榜（广告牌）的概括，同时跟踪语言生成任务和指标的进展。与通过预定度量分类提交系统的传统的单向排行榜不同，广告牌可接受发电机和评估度量作为竞争条目。广告牌会自动创建一个基于跨发电机的全局分析选择和线性地组合一些指标的集合度量。此外，指标基于与人类判断的相关性进行排序。我们释放了用于机器翻译，摘要和图像标题的四个广告牌。我们展示了一些多样化度量的线性集合有时会在隔离中显着优于现有的度量。我们的混合效果模型分析表明，大多数自动度量，尤其是基于参考的机器，对人类发电的重估，展示了更新度量的重要性，将来变得更强大（也许与人类更相似）。

Automatic machine translation (MT) metrics are widely used to distinguish the translation qualities of machine translation systems across relatively large test sets (system-level evaluation). However, it is unclear if automatic metrics are reliable at distinguishing good translations from bad translations at the sentence level (segment-level evaluation). In this paper, we investigate how useful MT metrics are at detecting the success of a machine translation component when placed in a larger platform with a downstream task. We evaluate the segment-level performance of the most widely used MT metrics (chrF, COMET, BERTScore, etc.) on three downstream cross-lingual tasks (dialogue state tracking, question answering, and semantic parsing). For each task, we only have access to a monolingual task-specific model. We calculate the correlation between the metric's ability to predict a good/bad translation with the success/failure on the final task for the Translate-Test setup. Our experiments demonstrate that all metrics exhibit negligible correlation with the extrinsic evaluation of the downstream outcomes. We also find that the scores provided by neural metrics are not interpretable mostly because of undefined ranges. Our analysis suggests that future MT metrics be designed to produce error labels rather than scores to facilitate extrinsic evaluation.

The proliferation of automatic faithfulness metrics for summarization has produced a need for benchmarks to evaluate them. While existing benchmarks measure the correlation with human judgements of faithfulness on model-generated summaries, they are insufficient for diagnosing whether metrics are: 1) consistent, i.e., decrease as errors are introduced into a summary, 2) effective on human-written texts, and 3) sensitive to different error types (as summaries can contain multiple errors). To address these needs, we present a benchmark of unfaithful minimal pairs (BUMP), a dataset of 889 human-written, minimally different summary pairs, where a single error (from an ontology of 7 types) is introduced to a summary from the CNN/DailyMail dataset to produce an unfaithful summary. We find BUMP complements existing benchmarks in a number of ways: 1) the summaries in BUMP are harder to discriminate and less probable under SOTA summarization models, 2) BUMP enables measuring the consistency of metrics, and reveals that the most discriminative metrics tend not to be the most consistent, 3) BUMP enables the measurement of metrics' performance on individual error types and highlights areas of weakness for future work.

图像字幕是当前的研究任务，用于使用场景中的对象及其关系来描述图像内容。为了应对这项任务，使用了两个重要的研究领域，人为的视觉和自然语言处理。在图像字幕中，就像在任何计算智能任务中一样，性能指标对于知道方法的性能（或坏）至关重要。近年来，已经观察到，基于n-gram的经典指标不足以捕获语义和关键含义来描述图像中的内容。为了衡量或不进行最新指标的集合，在本手稿中，我们对使用众所周知的COCO数据集进行了对几种图像字幕指标的评估以及它们之间的比较。为此，我们设计了两种情况。 1）一组人工构建字幕，以及2）比较某些最先进的图像字幕方法的比较。我们试图回答问题：当前的指标是否有助于制作高质量的标题？实际指标如何相互比较？指标真正测量什么？

We describe METEOR, an automatic metric for machine translation evaluation that is based on a generalized concept of unigram matching between the machineproduced translation and human-produced reference translations. Unigrams can be matched based on their surface forms, stemmed forms, and meanings; furthermore, METEOR can be easily extended to include more advanced matching strategies.Once all generalized unigram matches between the two strings have been found, METEOR computes a score for this matching using a combination of unigram-precision, unigram-recall, and a measure of fragmentation that is designed to directly capture how well-ordered the matched words in the machine translation are in relation to the reference. We evaluate METEOR by measuring the correlation between the metric scores and human judgments of translation quality. We compute the Pearson R correlation value between its scores and human quality assessments of the LDC TIDES 2003 Arabic-to-English and Chinese-to-English datasets.We perform segment-bysegment correlation, and show that METEOR gets an R correlation value of 0.347 on the Arabic data and 0.331 on the Chinese data. This is shown to be an improvement on using simply unigramprecision, unigram-recall and their harmonic F1 combination. We also perform experiments to show the relative contributions of the various mapping modules.