Dog whistles are coded expressions with dual meanings: one intended for the general public (outgroup) and another that conveys a specific message to an intended audience (ingroup). Often, these expressions are used to convey controversial political opinions while maintaining plausible deniability and slip by content moderation filters. Identification of dog whistles relies on curated lexicons, which have trouble keeping up to date. We introduce FETCH!, a task for finding novel dog whistles in massive social media corpora. We find that state-of-the-art systems fail to achieve meaningful results across three distinct social media case studies. We present EarShot, a strong baseline system that combines the strengths of vector databases and Large Language Models (LLMs) to efficiently and effectively identify new dog whistles.

Plain Language Summarization (PLS) aims to distill complex documents into accessible summaries for non-expert audiences. In this paper, we conduct a thorough survey of PLS literature, and identify that the current standard practice for readability evaluation is to use traditional readability metrics, such as Flesch-Kincaid Grade Level (FKGL). However, despite proven utility in other fields, these metrics have not been compared to human readability judgments in PLS. We evaluate 8 readability metrics and show that most correlate poorly with human judgments, including the most popular metric, FKGL. We then show that Language Models (LMs) are better judges of readability, with the best-performing model achieving a Pearson correlation of 0.56 with human judgments. Extending our analysis to PLS datasets, which contain summaries aimed at non-expert audiences, we find that LMs better capture deeper measures of readability, such as required background knowledge, and lead to different conclusions than the traditional metrics. Based on these findings, we offer recommendations for best practices in the evaluation of plain language summaries.

Authors seeking to communicate with broader audiences often share their ideas in various document formats, such as slide decks, newsletters, reports, and posters. Prior work on document generation has generally tackled the creation of each separate format to be a different task, leading to fragmented learning processes, redundancy in models and methods, and disjointed evaluation. We consider each of these documents as templatic views of the same underlying knowledge/content, and we aim to unify the generation and evaluation of these templatic views. We begin by showing that current LLMs are capable of generating various document formats with little to no supervision. Further, a simple augmentation involving a structured intermediate representation can improve performance, especially for smaller models. We then introduce a novel unified evaluation framework that can be adapted to measuring the quality of document generators for heterogeneous downstream applications. This evaluation is adaptable to a range of user defined criteria and application scenarios, obviating the need for task specific evaluation metrics. Finally, we conduct a human evaluation, which shows that people prefer 82% of the documents generated with our method, while correlating more highly with our unified evaluation framework than prior metrics in the literature.

Recently, work in NLP has shifted to few-shot (in-context) learning, with large language models (LLMs) performing well across a range of tasks. However, while fairness evaluations have become a standard for supervised methods, little is known about the fairness of LLMs as prediction systems. Further, common standard methods for fairness involve access to model weights or are applied during finetuning, which are not applicable in few-shot learning. Do LLMs exhibit prediction biases when used for standard NLP tasks?In this work, we analyze the effect of shots, which directly affect the performance of models, on the fairness of LLMs as NLP classification systems. We consider how different shot selection strategies, both existing and new demographically sensitive methods, affect model fairness across three standard fairness datasets. We find that overall the performance of LLMs is not indicative of their fairness, and there is not a single method that fits all scenarios. In light of these facts, we discuss how future work can include LLM fairness in evaluations.

Machine learning models that offer excellent predictive performance often lack the interpretability necessary to support integrated human machine decision-making. In clinical medicine and other high-risk settings, domain experts may be unwilling to trust model predictions without explanations. Work in explainable AI must balance competing objectives along two different axes: 1) Models should ideally be both accurate and simple. 2) Explanations must balance faithfulness to the model’s decision-making with their plausibility to a domain expert. We propose to use knowledge distillation, or training a student model that mimics the behavior of a trained teacher model, as a technique to generate faithful and plausible explanations. We evaluate our approach on the task of assigning ICD codes to clinical notes to demonstrate that the student model is faithful to the teacher model’s behavior and produces quality natural language explanations.

We address the task of explaining relationships between two scientific documents using natural language text. This task requires modeling the complex content of long technical documents, deducing a relationship between these documents, and expressing the details of that relationship in text. In addition to the theoretical interest of this task, successful solutions can help improve researcher efficiency in search and review. In this paper we establish a dataset of 622K examples from 154K documents. We pretrain a large language model to serve as the foundation for autoregressive approaches to the task. We explore the impact of taking different views on the two documents, including the use of dense representations extracted with scientific IE systems. We provide extensive automatic and human evaluations which show the promise of such models, but make clear challenges for future work.

We introduce TLDR generation, a new form of extreme summarization, for scientific papers. TLDR generation involves high source compression and requires expert background knowledge and understanding of complex domain-specific language. To facilitate study on this task, we introduce SCITLDR, a new multi-target dataset of 5.4K TLDRs over 3.2K papers. SCITLDR contains both author-written and expert-derived TLDRs, where the latter are collected using a novel annotation protocol that produces high-quality summaries while minimizing annotation burden. We propose CATTS, a simple yet effective learning strategy for generating TLDRs that exploits titles as an auxiliary training signal. CATTS improves upon strong baselines under both automated metrics and human evaluations. Data and code are publicly available at https://github.com/allenai/scitldr.

Vulgarity is a common linguistic expression and is used to perform several linguistic functions. Understanding their usage can aid both linguistic and psychological phenomena as well as benefit downstream natural language processing applications such as sentiment analysis. This study performs a large-scale, data-driven empirical analysis of vulgar words using social media data. We analyze the socio-cultural and pragmatic aspects of vulgarity using tweets from users with known demographics. Further, we collect sentiment ratings for vulgar tweets to study the relationship between the use of vulgar words and perceived sentiment and show that explicitly modeling vulgar words can boost sentiment analysis performance.

Vulgar words are employed in language use for several different functions, ranging from expressing aggression to signaling group identity or the informality of the communication. This versatility of usage of a restricted set of words is challenging for downstream applications and has yet to be studied quantitatively or using natural language processing techniques. We introduce a novel data set of 7,800 tweets from users with known demographic traits where all instances of vulgar words are annotated with one of the six categories of vulgar word use. Using this data set, we present the first analysis of the pragmatic aspects of vulgarity and how they relate to social factors. We build a model able to predict the category of a vulgar word based on the immediate context it appears in with 67.4 macro F1 across six classes. Finally, we demonstrate the utility of modeling the type of vulgar word use in context by using this information to achieve state-of-the-art performance in hate speech detection on a benchmark data set.