自由文本的理由旨在通过自然语言更灵活,直观地解释神经语言模型(LM)行为。为了确保理由质量,重要的是要拥有衡量理由的忠诚度(反映了LM的实际行为)和合理性(对人类的说服力)很重要。所有现有的自由文本理由指标均基于模拟性(基本原理与LM预测标签之间的关联),但没有评估此类指标可靠性的协议。为了调查这一点,我们提出了框架,该框架是评估自由文本理由的模拟性指标的框架。框架基于三个公理:(1)良好的指标应为参考理由产生最高的分数,从而最大程度地逐构构建标签标签的关联; (2)良好的指标应适当地对理由的语义扰动敏感; (3)良好的指标应该对LM的任务性能的变化具有鲁棒性。在三个文本分类数据集中,我们表明现有的可模拟性指标无法满足所有三个帧公理,因为它们是通过模型预处理实现的,该模型预处理弄乱了度量标准的信号。我们介绍了一种非原始的模拟性变体,该变体将(1)和(3)的性能平均提高41.7%和42.9%,同时在(2)上进行竞争性能。
translated by 谷歌翻译
Free-text rationales (FTRs) follow how humans communicate by explaining reasoning processes via natural language. A number of recent works have studied how to improve language model (LM) generalization by using FTRs to teach LMs the correct reasoning processes behind correct task outputs. These prior works aim to learn from FTRs by appending them to the LM input or target output, but this may introduce an input distribution shift or conflict with the task objective, respectively. We propose KNIFE, which distills FTR knowledge from an FTR-augmented teacher LM (takes both task input and FTR) to a student LM (takes only task input), which is used for inference. Crucially, the teacher LM's forward computation has a bottleneck stage in which all of its FTR states are masked out, which pushes knowledge from the FTR states into the task input/output states. Then, FTR knowledge is distilled to the student LM by training its task input/output states to align with the teacher LM's. On two question answering datasets, we show that KNIFE significantly outperforms existing FTR learning methods, in both fully-supervised and low-resource settings.
translated by 谷歌翻译
Neural language models (LMs) have achieved impressive results on various language-based reasoning tasks by utilizing latent knowledge encoded in their own pretrained parameters. To make this reasoning process more explicit, recent works retrieve a rationalizing LM's internal knowledge by training or prompting it to generate free-text rationales, which can be used to guide task predictions made by either the same LM or a separate reasoning LM. However, rationalizing LMs require expensive rationale annotation and/or computation, without any assurance that their generated rationales improve LM task performance or faithfully reflect LM decision-making. In this paper, we propose PINTO, an LM pipeline that rationalizes via prompt-based learning, and learns to faithfully reason over rationales via counterfactual regularization. First, PINTO maps out a suitable reasoning process for the task input by prompting a frozen rationalizing LM to generate a free-text rationale. Second, PINTO's reasoning LM is fine-tuned to solve the task using the generated rationale as context, while regularized to output less confident predictions when the rationale is perturbed. Across four datasets, we show that PINTO significantly improves the generalization ability of the reasoning LM, yielding higher performance on both in-distribution and out-of-distribution test sets. Also, we find that PINTO's rationales are more faithful to its task predictions than those generated by competitive baselines.
translated by 谷歌翻译
通过突出显示最大影响输出的文本输入,提取理由对给定任务实例的预测解释了语言模型(LM)预测。理想情况下,理由提取应该是忠诚的(反映LM的行为),合理的(对人类来说),数据效率和快速,而不牺牲LM的任务表现。先前的基本原理提取工程由专门的方法提供解决这些desiderata的各个子集 - 但从来没有五个。狭隘地关注某些Desiderata通常会以忽略的牺牲品为代价,因此现有的理由提取器在现实世界应用中往往是不切实际的。为了解决这一挑战,我们提出了Unirex,统一和高度灵活的理由提取学习框架,允许用户容易地占所有五个因素。 UNIREX使理论提取器培训过程的端到端定制,支持任意:(1)启发式/学习的理由提取者,(2)忠诚和/或合理性目标的组合,以及(3)金理由监管的数额。在三个文本分类数据集中,我们最好的UNIrex配置实现了与强基线相比的五个desiderata的较高余额。此外,Unirex培训的理由提取器甚至可以推广到看不见的数据集和任务。
translated by 谷歌翻译
在可解释的NLP中,我们需要忠实的理由,以反映模型的解释实例的决策过程。虽然先前的工作着重于提取理由(输入词的子集),但我们研究了他们研究较少的对应物:自由文本的自然语言理由。我们证明,对信息摘要样式任务的忠实提取合理化的现有模型的管道并没有可靠地扩展到需要自由文本理性的“推理”任务。我们转向共同预测和合理化的模型,这是一类广泛使用的高性能模型,用于自由文本合理化,尚未确定忠诚。我们将标签理性关联定义为忠诚的必要特性:产生标签和原理的模型的内部机制必须有意义地关联。我们提出了两项​​测量来测试此属性的测量:鲁棒性等效性和特征重要性一致性。我们发现,基于T5的最先进的联合模型表现出合理化常识性提问和自然语言推论的两种属性,表明它们有可能产生忠实的自由文本理性。
translated by 谷歌翻译
预测任务标签和为其预测生成自由文本阐述的自律化模型可以实现与NLP系统更直观的交互。然而,这些模型目前正在接受大量人为的自由文本解释,每个任务都会阻碍更广泛的使用。我们建议使用少数培训例子研究更现实的自律化建立。我们出示2月 - 一个标准化的四个现有英语数据集和相关指标。我们通过2月份广泛探索自然语言提示来确定正确的提示方法。然后,通过使用此提示并缩放模型大小,我们证明了几次拍摄自合合理化的进展。我们展示了这项任务的完善房间仍然有充足的改进空间:人类注册人评估的生成解释的平均合理性最多为51%,而人类解释的合理性是76%。我们希望2月份与我们的拟议方法一起促使社区承担几次拍摄的自我合理化挑战。
translated by 谷歌翻译
尽管预训练的语言模型(LMS)在许多NLP任务中都取得了重大改进,但人们越来越关注探索LMS的能力并解释其预测。但是,现有作品通常仅着眼于某些下游任务的特定功能。缺乏直接评估蒙版单词预测性能和预训练LMS的解释性的数据集。为了填补空白,我们提出了一个新颖的评估基准,以提供英语和中文注释的数据。它在多个维度(即语法,语义,知识,推理和计算)中测试LMS能力。此外,它提供了满足足够和紧凑性的仔细注释的令牌级别的理由。它包含每个原始实例的扰动实例,以便将扰动下的基本原理一致性用作忠实的指标,即解释性的观点。我们在几个广泛使用的预训练的LMS上进行实验。结果表明,他们在知识和计算的维度上表现较差。而且它们在所有维度上的合理性远非令人满意,尤其是当理由缩短时。此外,我们评估的预训练的LMS在语法感知数据上并不强大。我们将以\ url {http:// xyz}发布此评估基准,并希望它可以促进预训练的LMS的研究进度。
translated by 谷歌翻译
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。
translated by 谷歌翻译
Large language models show improved downstream task performance when prompted to generate step-by-step reasoning to justify their final answers. These reasoning steps greatly improve model interpretability and verification, but objectively studying their correctness (independent of the final answer) is difficult without reliable methods for automatic evaluation. We simply do not know how often the stated reasoning steps actually support the final end task predictions. In this work, we present ROSCOE, a suite of interpretable, unsupervised automatic scores that improve and extend previous text generation evaluation metrics. To evaluate ROSCOE against baseline metrics, we design a typology of reasoning errors and collect synthetic and human evaluation scores on commonly used reasoning datasets. In contrast with existing metrics, ROSCOE can measure semantic consistency, logicality, informativeness, fluency, and factuality - among other traits - by leveraging properties of step-by-step rationales. We empirically verify the strength of our metrics on five human annotated and six programmatically perturbed diagnostics datasets - covering a diverse set of tasks that require reasoning skills and show that ROSCOE can consistently outperform baseline metrics.
translated by 谷歌翻译
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。
translated by 谷歌翻译
人类使用自然语言来撰写普通概念,将他们的环境归结为合理的日常场景描述。然而,这种生成的致辞推理(GCSR)技能缺乏最先进的文本生成方法。关于由神经文本生成模型(例如,预先接受的文本到文本变压器)生成的任意概念的描述性句子通常是语法流畅的,但可能与人类常识不相符,这主要是由于它们缺乏捕获概念关系的机制识别隐式概念,并对看不见的概念组成来执行概括的推理。在本文中,我们提出了一种想象的 - 言语(I&V)方法,其学会在输入概念之间的关系中想象一个关系场景知识图(SKG),并在生成合理的场景描述时利用SKG作为约束。我们收集和协调来自不同领域和方式的一套知识资源,为I&v提供丰富的辅助监督信号。该实验展示了I&V在提高概念到句子和概念到故事的生成任务上的语言模型的有效性,同时使模型能够从更少的任务示例中学习并生成对人类注入者常识的SKG。
translated by 谷歌翻译
人工智能的最新趋势是将验证的模型用于语言和视觉任务,这些模型已经实现了非凡的表现,但也令人困惑。因此,以各种方式探索这些模型的能力对该领域至关重要。在本文中,我们探讨了模型的可靠性,在其中我们将可靠的模型定义为一个不仅可以实现强大的预测性能,而且在许多涉及不确定性(例如选择性预测,开放式设置识别)的决策任务上,在许多决策任务上表现出色,而且表现良好。强大的概括(例如,准确性和适当的评分规则,例如在分布数据集中和分发数据集上的对数可能性)和适应性(例如,主动学习,几乎没有射击不确定性)。我们设计了40个数据集的10种任务类型,以评估视觉和语言域上可靠性的不同方面。为了提高可靠性,我们分别开发了VIT-PLEX和T5-PLEX,分别针对视觉和语言方式扩展了大型模型。 PLEX极大地改善了跨可靠性任务的最先进,并简化了传统协议,因为它可以改善开箱即用的性能,并且不需要设计分数或为每个任务调整模型。我们演示了高达1B参数的模型尺寸的缩放效果,并预处理数据集大小最多4B示例。我们还展示了PLEX在具有挑战性的任务上的功能,包括零射门的开放式识别,主动学习和对话语言理解中的不确定性。
translated by 谷歌翻译
Meta-training, which fine-tunes the language model (LM) on various downstream tasks by maximizing the likelihood of the target label given the task instruction and input instance, has improved the zero-shot task generalization performance. However, meta-trained LMs still struggle to generalize to challenging tasks containing novel labels unseen during meta-training. In this paper, we propose Flipped Learning, an alternative method of meta-training which trains the LM to generate the task instruction given the input instance and label. During inference, the LM trained with Flipped Learning, referred to as Flipped, selects the label option that is most likely to generate the task instruction. On 14 tasks of the BIG-bench benchmark, the 11B-sized Flipped outperforms zero-shot T0-11B and even a 16 times larger 3-shot GPT-3 (175B) on average by 8.4% and 9.7% points, respectively. Flipped gives particularly large improvements on tasks with unseen labels, outperforming T0-11B by up to +20% average F1 score. This indicates that the strong task generalization of Flipped comes from improved generalization to novel labels. We release our code at https://github.com/seonghyeonye/Flipped-Learning.
translated by 谷歌翻译
使用知识图(KGS)增强预培训的语言模型在各种型号推理任务方面取得了成功。但是,对于给定的任务实例,kg或kg的某些部分可能没有用。虽然kg-cugmented模型经常使用注意力集中在特定的kg组件上,但仍然始终使用kg,并且从未明确教授应该使用关注机制。同时,显着性方法可以测量kg特征(例如,图形,节点,路径)对模型进行正确预测的影响,从而解释了哪个kg特征是有用的。本文探讨了可用于提高kg增强模型的性能的显着性解释。首先,我们建议创建粗(是kg有用的?)和精细(kg中的节点/路径是有用的?)显着解释。其次,为了激励基于显着的监督,我们分析了Oracle kg-angimented模型,即直接使用显着解释作为引导他们注意的额外输入。第三,我们提出Salkg,kg-ug-anded模型的框架,以从粗糙和/或罚款解释中学习。给定从任务的培训集创建的显着解释,Salkg共同列举模型来预测解释,然后通过参加预测的解释突出显示的kg功能来解决任务。在三个型号QA基准(CSQA,OBQA,Codah)和一系列KG增强模型中,我们表明Salkg可以产生相当大的性能增益 - 对CSQA的绝对改善高达2.76%。
translated by 谷歌翻译
我们提出了两种小型无监督方法,用于消除文本中的毒性。我们的第一个方法结合了最近的两个想法:(1)使用小型条件语言模型的生成过程的指导和(2)使用释义模型进行风格传输。我们使用良好的令人措辞的令人愉快的释放器,由风格培训的语言模型引导,以保持文本内容并消除毒性。我们的第二种方法使用BERT用他们的非攻击性同义词取代毒性单词。我们通过使BERT替换具有可变数量的单词的屏蔽令牌来使该方法更灵活。最后,我们介绍了毒性去除任务的风格转移模型的第一个大规模比较研究。我们将模型与许多用于样式传输的方法进行比较。使用无监督的样式传输指标的组合以可参考方式评估该模型。两种方法都建议产生新的SOTA结果。
translated by 谷歌翻译
Language models (LMs) often generate incoherent outputs: they refer to events and entity states that are incompatible with the state of the world described in their inputs. We introduce SituationSupervision, a family of approaches for improving coherence in LMs by training them to construct and condition on explicit representations of entities and their states. SituationSupervision has two components: an auxiliary situation modeling task that trains models to predict state representations in context, and a latent state inference procedure that imputes these states from partially annotated training data. SituationSupervision can be applied to both fine-tuning (by supervising LMs to encode state variables in their hidden representations) and prompting (by inducing LMs to interleave textual descriptions of entity states with output text). In both cases, SituationSupervision requires only a small number of state annotations to produce major coherence improvements (between 4-11%), showing that standard LMs can be sample-efficiently trained to model not just language but the situations it describes.
translated by 谷歌翻译
基于变压器的语言模型最近在许多自然语言任务中取得了显着的结果。但是,通常通过利用大量培训数据来实现排行榜的性能,并且很少通过将明确的语言知识编码为神经模型。这使许多人质疑语言学对现代自然语言处理的相关性。在本文中,我介绍了几个案例研究,以说明理论语言学和神经语言模型仍然相互关联。首先,语言模型通过提供一个客观的工具来测量语义距离,这对语言学家很有用,语义距离很难使用传统方法。另一方面,语言理论通过提供框架和数据源来探究我们的语言模型,以了解语言理解的特定方面,从而有助于语言建模研究。本论文贡献了三项研究,探讨了语言模型中语法 - 听觉界面的不同方面。在论文的第一部分中,我将语言模型应用于单词类灵活性的问题。我将Mbert作为语义距离测量的来源,我提供了有利于将单词类灵活性分析为方向过程的证据。在论文的第二部分中,我提出了一种方法来测量语言模型中间层的惊奇方法。我的实验表明,包含形态句法异常的句子触发了语言模型早期的惊喜,而不是语义和常识异常。最后,在论文的第三部分中,我适应了一些心理语言学研究,以表明语言模型包含了论证结构结构的知识。总而言之,我的论文在自然语言处理,语言理论和心理语言学之间建立了新的联系,以为语言模型的解释提供新的观点。
translated by 谷歌翻译
诸如“玻璃可以用于饮用水”之类的先决条件的推理仍然是语言模型的开放问题。主要的挑战在于,前提数据的稀缺性以及模型对这种推理的缺乏支持。我们提出了粉红色的,预处理性的推论,并通过弱监督进行了改进的模型,用于通过最低限度的监督来推理前提条件。我们从经验和理论上表明,粉红色改善了基准的结果,该基准的重点是通过常识性知识的前提(高达40%的宏F1分数)进行推理。我们通过Pac-Bayesian信息分析,精确度量和消融研究进一步研究粉红色。
translated by 谷歌翻译
Question-answering datasets require a broad set of reasoning skills. We show how to use question decompositions to teach language models these broad reasoning skills in a robust fashion. Specifically, we use widely available QDMR representations to programmatically create hard-to-cheat synthetic contexts for real questions in six multi-step reasoning datasets. These contexts are carefully designed to avoid reasoning shortcuts prevalent in real contexts that prevent models from learning the right skills. This results in a pretraining dataset, named TeaBReaC, containing 525K multi-step questions (with associated formal programs) covering about 900 reasoning patterns. We show that pretraining standard language models (LMs) on TeaBReaC before fine-tuning them on target datasets improves their performance by up to 13 F1 points across 4 multi-step QA datasets, with up to 21 point gain on more complex questions. The resulting models also demonstrate higher robustness, with a 5-8 F1 point improvement on two contrast sets. Furthermore, TeaBReaC pretraining substantially improves model performance and robustness even when starting with numerate LMs pretrained using recent methods (e.g., PReasM, POET). Our work thus shows how to effectively use decomposition-guided contexts to robustly teach multi-step reasoning.
translated by 谷歌翻译
Transformers have been shown to be able to perform deductive reasoning on a logical rulebase containing rules and statements written in English natural language. While the progress is promising, it is currently unclear if these models indeed perform logical reasoning by understanding the underlying logical semantics in the language. To this end, we propose RobustLR, a suite of evaluation datasets that evaluate the robustness of these models to minimal logical edits in rulebases and some standard logical equivalence conditions. In our experiments with RoBERTa and T5, we find that the models trained in prior works do not perform consistently on the different perturbations in RobustLR, thus showing that the models are not robust to the proposed logical perturbations. Further, we find that the models find it especially hard to learn logical negation and disjunction operators. Overall, using our evaluation sets, we demonstrate some shortcomings of the deductive reasoning-based language models, which can eventually help towards designing better models for logical reasoning over natural language. All the datasets and code base have been made publicly available.
translated by 谷歌翻译