QuALITY: Question Answering with Long Input Texts, Yes!

To enable building and testing models on long-document comprehension, we introduce QuALITY, a multiple-choice QA dataset with context passages in English that have an average length of about 5,000 tokens, much longer than typical current models can process. Unlike in prior work with passages, our questions are written and validated by contributors who have read the entire passage, rather than relying on summaries or excerpts. In addition, only half of the questions are answerable by annotators working under tight time constraints, indicating that skimming and simple search are not enough to consistently perform well. Current models perform poorly on this task (55.4%) and significantly lag behind human performance (93.5%).

Adversarially Constructed Evaluation Sets Are More Challenging, but May Not Be Fair

More capable language models increasingly saturate existing task benchmarks, in some cases outperforming humans. This has left little headroom with which to measure further progress. Adversarial dataset creation has been proposed as a strategy to construct more challenging datasets, and two common approaches are: (1) filtering out easy examples and (2) model-in-the-loop data collection. In this work, we study the impact of applying each approach to create more challenging evaluation datasets. We adapt the AFLite algorithm to filter evaluation data, and run experiments against 18 different adversary models. We find that AFLite indeed selects more challenging examples, lowering the performance of evaluated models more as stronger adversary models are used. However, the resulting ranking of models can also be unstable and highly sensitive to the choice of adversary model used. Moreover, AFLite oversamples examples with low annotator agreement, meaning that model comparisons hinge on the most contentiously labeled examples. Smaller-scale experiments on the adversarially collected datasets ANLI and AdversarialQA show similar findings, broadly lowering performance with stronger adversaries while disproportionately affecting the adversary model.

Learning with Noisy Labels by Targeted Relabeling

Crowdsourcing platforms are often used to collect datasets for training deep neural networks, despite higher levels of inaccurate labeling compared to expert labeling. There are two common strategies to manage the impact of this noise, the first involves aggregating redundant annotations, but comes at the expense of labeling substantially fewer examples. Secondly, prior works have also considered using the entire annotation budget to label as many examples as possible and subsequently apply denoising algorithms to implicitly clean up the dataset. We propose an approach which instead reserves a fraction of annotations to explicitly relabel highly probable labeling errors. In particular, we allocate a large portion of the labeling budget to form an initial dataset used to train a model. This model is then used to identify specific examples that appear most likely to be incorrect, which we spend the remaining budget to relabel. Experiments across three model variations and four natural language processing tasks show our approach outperforms both label aggregation and advanced denoising methods designed to handle noisy labels when allocated the same annotation budget.

When Combating Hype, Proceed with Caution

In an effort to avoid reinforcing widespread hype about the capabilities of state-of-the-art language technology, researchers have developed practices in framing and citation that serve to deemphasize the field's successes. Though well-meaning, these practices often yield misleading or even false claims about the limits of our best technology. This is a problem, and it may be more serious than it looks: It limits our ability to mitigate short-term harms from NLP deployments and it limits our ability to prepare for the potentially enormous impacts of more distant future advances. This paper urges researchers to be careful about these claims and suggests some research directions and communication strategies that will make it easier to avoid or rebut them.

BBQ: A Hand-Built Bias Benchmark for Question Answering

It is well documented that NLP models learn social biases present in the world, but little work has been done to show how these biases manifest in actual model outputs for applied tasks like question answering (QA). We introduce the Bias Benchmark for QA (BBQ), a dataset consisting of question-sets constructed by the authors that highlight \textit{attested} social biases against people belonging to protected classes along nine different social dimensions relevant for U.S. English-speaking contexts. Our task evaluates model responses at two distinct levels: (i) given an under-informative context, test how strongly model answers reflect social biases, and (ii) given an adequately informative context, test whether the model's biases still override a correct answer choice. We find that models strongly rely on stereotypes when the context is ambiguous, meaning that the model's outputs consistently reproduce harmful biases in this setting. Though models are much more accurate when the context provides an unambiguous answer, they still rely on stereotyped information and achieve an accuracy 2.5 percentage points higher on examples where the correct answer aligns with a social bias, with this accuracy difference widening to 5 points for examples targeting gender.

Fine-Tuned Transformers Show Clusters of Similar Representations Across Layers

Despite the success of fine-tuning pretrained language encoders like BERT for downstream natural language understanding (NLU) tasks, it is still poorly understood how neural networks change after fine-tuning. In this work, we use centered kernel alignment (CKA), a method for comparing learned representations, to measure the similarity of representations in task-tuned models across layers. In experiments across twelve NLU tasks, we discover a consistent block diagonal structure in the similarity of representations within fine-tuned RoBERTa and ALBERT models, with strong similarity within clusters of earlier and later layers, but not between them. The similarity of later layer representations implies that later layers only marginally contribute to task performance, and we verify in experiments that the top few layers of fine-tuned Transformers can be discarded without hurting performance, even with no further tuning.

NOPE: A Corpus of Naturally-Occurring Presuppositions in English

Understanding language requires grasping not only the overtly stated content, but also making inferences about things that were left unsaid. These inferences include presuppositions, a phenomenon by which a listener learns about new information through reasoning about what a speaker takes as given. Presuppositions require complex understanding of the lexical and syntactic properties that trigger them as well as the broader conversational context. In this work, we introduce the Naturally-Occurring Presuppositions in English (NOPE) Corpus to investigate the context-sensitivity of 10 different types of presupposition triggers and to evaluate machine learning models' ability to predict human inferences. We find that most of the triggers we investigate exhibit moderate variability. We further find that transformer-based models draw correct inferences in simple cases involving presuppositions, but they fail to capture the minority of exceptional cases in which human judgments reveal complex interactions between context and triggers.

Comparing Test Sets with Item Response Theory

Recent years have seen numerous NLP datasets introduced to evaluate the performance of fine-tuned models on natural language understanding tasks. Recent results from large pretrained models, though, show that many of these datasets are largely saturated and unlikely to be able to detect further progress. What kind of datasets are still effective at discriminating among strong models, and what kind of datasets should we expect to be able to detect future improvements? To measure this uniformly across datasets, we draw on Item Response Theory and evaluate 29 datasets using predictions from 18 pretrained Transformer models on individual test examples. We find that Quoref, HellaSwag, and MC-TACO are best suited for distinguishing among state-of-the-art models, while SNLI, MNLI, and CommitmentBank seem to be saturated for current strong models. We also observe span selection task format, which is used for QA datasets like QAMR or SQuAD2.0, is effective in differentiating between strong and weak models.

What Ingredients Make for an Effective Crowdsourcing Protocol for Difficult NLU Data Collection Tasks?

Crowdsourcing is widely used to create data for common natural language understanding tasks. Despite the importance of these datasets for measuring and refining model understanding of language, there has been little focus on the crowdsourcing methods used for collecting the datasets. In this paper, we compare the efficacy of interventions that have been proposed in prior work as ways of improving data quality. We use multiple-choice question answering as a testbed and run a randomized trial by assigning crowdworkers to write questions under one of four different data collection protocols. We find that asking workers to write explanations for their examples is an ineffective stand-alone strategy for boosting NLU example difficulty. However, we find that training crowdworkers, and then using an iterative process of collecting data, sending feedback, and qualifying workers based on expert judgments is an effective means of collecting challenging data. But using crowdsourced, instead of expert judgments, to qualify workers and send feedback does not prove to be effective. We observe that the data from the iterative protocol with expert assessments is more challenging by several measures. Notably, the human--model gap on the unanimous agreement portion of this data is, on average, twice as large as the gap for the baseline protocol data.

Does Putting a Linguist in the Loop Improve NLU Data Collection?

Many crowdsourced NLP datasets contain systematic gaps and biases that are identified only after data collection is complete. Identifying these issues from early data samples during crowdsourcing should make mitigation more efficient, especially when done iteratively. We take natural language inference as a test case and ask whether it is beneficial to put a linguist `in the loop' during data collection to dynamically identify and address gaps in the data by introducing novel constraints on the task. We directly compare three data collection protocols: (i) a baseline protocol, (ii) a linguist-in-the-loop intervention with iteratively-updated constraints on the task, and (iii) an extension of linguist-in-the-loop that provides direct interaction between linguists and crowdworkers via a chatroom. The datasets collected with linguist involvement are more reliably challenging than baseline, without loss of quality. But we see no evidence that using this data in training leads to better out-of-domain model performance, and the addition of a chat platform has no measurable effect on the resulting dataset. We suggest integrating expert analysis \textit{during} data collection so that the expert can dynamically address gaps and biases in the dataset.