Consistency of a model -- that is, the invariance of its behavior under meaning-preserving alternations in its input -- is a highly desirable property in natural language processing. In this paper we study the question: Are Pretrained Language Models (PLMs) consistent with respect to factual knowledge? To this end, we create ParaRel, a high-quality resource of cloze-style query English paraphrases. It contains a total of 328 paraphrases for 38 relations. Using ParaRel, we show that the consistency of all PLMs we experiment with is poor -- though with high variance between relations. Our analysis of the representational spaces of PLMs suggests that they have a poor structure and are currently not suitable for representing knowledge robustly. Finally, we propose a method for improving model consistency and experimentally demonstrate its effectiveness.
Massachusetts Institute of Technology（麻省理工学院）；Intel AI（英特尔人工智能）；Mila；McGill University（麦吉尔大学）
A stereotype is an over-generalized belief about a particular group of people, e.g., Asians are good at math or Asians are bad drivers. Such beliefs (biases) are known to hurt target groups. Since pretrained language models are trained on large real world data, they are known to capture stereotypical biases. In order to assess the adverse effects of these models, it is important to quantify the bias captured in them. Existing literature on quantifying bias evaluates pretrained language models on a small set of artificially constructed bias-assessing sentences. We present StereoSet, a large-sca…
KU Leuven（鲁汶大学）；University of Antwerp（安特卫普大学）；TU Berlin（柏林工业大学）
An increasing awareness of biased patterns in natural language processing resources, like BERT, has motivated many metrics to quantify `bias' and `fairness'. But comparing the results of different metrics and the works that evaluate with such metrics remains difficult, if not outright impossible. We survey the existing literature on fairness metrics for pretrained language models and experimentally evaluate compatibility, including both biases in language models as in their downstream tasks. We do this by a mixture of traditional literature survey and correlation analysis, as well as by runnin…
Consistency, which refers to the capability of generating the same predictions for semantically similar contexts, is a highly desirable property for a sound language understanding model. Although recent pretrained language models (PLMs) deliver outstanding performance in various downstream tasks, they should exhibit consistent behaviour provided the models truly understand language. In this paper, we propose a simple framework named consistency analysis on language understanding models (CALUM)} to evaluate the model's lower-bound consistency ability. Through experiments, we confirmed that curr…
Bar-Ilan University（巴伊兰大学）；Allen Institute for Artificial Intelligence（艾伦人工智能研究所）；LMU Munich（慕尼黑大学）；Technion（以色列理工学院）；Carnegie Mellon University（卡内基梅隆大学）；Saarland University（萨尔大学）
Large amounts of training data are one of the major reasons for the high performance of state-of-the-art NLP models. But what exactly in the training data causes a model to make a certain prediction? We seek to answer this question by providing a language for describing how training data influences predictions, through a causal framework. Importantly, our framework bypasses the need to retrain expensive models and allows us to estimate causal effects based on observational data alone. Addressing the problem of extracting factual knowledge from pretrained language models (PLMs), we focus on sim…
Researchers have devised numerous ways to quantify social biases vested in pretrained language models. As some language models are capable of generating coherent completions given a set of textual prompts, several prompting datasets have been proposed to measure biases between social groups -- posing language generation as a way of identifying biases. In this opinion paper, we analyze how specific choices of prompt sets, metrics, automatic tools and sampling strategies affect bias results. We find out that the practice of measuring biases through text completion is prone to yielding contradict…
Quantitative Measurement of Language Distance among Closely Related Indo-European Languages Using Pretrained Language Models: A Case Study on the North Germanic Branch
This paper proposes a novel prompt-based finetuning method (called DLM-SCS) for few-shot text classification by utilizing the discriminative language model ELECTRA that is pretrained to distinguish whether a token is original or generated. The underlying idea is that the prompt instantiated with the true label should have higher semantic consistency score than other prompts with false labels. Since a prompt usually consists of several components (or parts), its semantic consistency can be decomposed accordingly. The semantic consistency of each component is then computed by making use of the p…
Pretrained multilingual language models can help bridge the digital language divide, enabling high-quality NLP models for lower resourced languages. Studies of multilingual models have so far focused on performance, consistency, and cross-lingual generalisation. However, with their wide-spread application in the wild and downstream societal impact, it is important to put multilingual models under the same scrutiny as monolingual models. This work investigates the group fairness of multilingual models, asking whether these models are equally fair across languages. To this end, we create a new f…
Measuring the similarity between two different sentential arguments is an important task in argument mining. However, one of the challenges in this field is that the dataset must be annotated using expertise in a variety of topics, making supervised learning with labeled data expensive. In this paper, we investigated whether this problem could be alleviated through transfer learning. We first adapted a pretrained language model to a domain of interest using self-supervised learning. Then, we fine-tuned the model to a task of measuring the similarity between sentences taken from different domai…
Filipino Benchmarks for Measuring Sexist and Homophobic Bias in Multilingual Language Models from Southeast Asia
School of Computer Science, University of Birmingham（英国伯明翰大学计算机科学学院）；Department of Information Systems and Computer Science, Ateneo de Manila University（马尼拉亚托大学信息系统与计算机科学系）
Chronologic: Measuring Language Models' Ability to Represent the Past
University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）；University of British Columbia（不列颠哥伦比亚大学）；University of Missouri（密苏里大学）；Cornell University（康奈尔大学）
RoCode: A Dataset for Measuring Code Intelligence from Problem Definitions in Romanian
University POLITEHNICA of Bucharest（布加勒斯特理工大学）；University of Bucharest, HTL Research Center（布加勒斯特大学HTL研究中心）；PRHLT Research Center, Universitat Politècnica de València（瓦伦西亚理工大学PRHLT研究中心）；ValgrAI - Valencian Graduate School and Research Network of Artificial Intelligence（ValgrAI - 瓦伦西亚人工智能研究生院与研究网络）
Pretrained language models, especially masked language models (MLMs) have seen success across many NLP tasks. However, there is ample evidence that they use the cultural biases that are undoubtedly present in the corpora they are trained on, implicitly creating harm with biased representations. To measure some forms of social bias in language models against protected demographic groups in the US, we introduce the Crowdsourced Stereotype Pairs benchmark (CrowS-Pairs). CrowS-Pairs has 1508 examples that cover stereotypes dealing with nine types of bias, like race, religion, and age. In CrowS-Pai…
The Ohio State University（俄亥俄州立大学）；Bloomberg（彭博社）；Google Research（谷歌研究院）；Johns Hopkins University（约翰斯·霍普金斯大学）
Expressing natural language descriptions of structured facts or relations -- data-to-text generation (D2T) -- increases the accessibility of structured knowledge repositories. Previous work shows that pre-trained language models(PLMs) perform remarkably well on this task after fine-tuning on a significant amount of task-specific training data. On the other hand, while auto-regressive PLMs can generalize from a few task examples, their efficacy at D2T is largely unexplored. Furthermore, we have an incomplete understanding of the limits of PLMs on D2T. In this work, we conduct an empirical study…
Cross-Lingual Consistency of Factual Knowledge in Multilingual Language Models
Center for Language and Cognition, University of Groningen（格罗宁根大学语言与认知中心）；Institute for Logic, Language and Computation, University of Amsterdam（阿姆斯特丹大学逻辑、语言与计算研究所）
