Causal reasoning, a core aspect of human cognition, is essential for advancing large language models (LLMs) towards artificial general intelligence (AGI) and reducing their propensity for generating hallucinations. However, existing datasets for evaluating causal reasoning in LLMs are limited by narrow domain coverage and a focus on cause-to-effect reasoning through textual problems, which does not comprehensively assess whether LLMs truly grasp causal relationships or merely guess correct answers. To address these shortcomings, we introduce a novel benchmark that spans textual, mathematical, and coding problem domains. Each problem is crafted to probe causal understanding from four perspectives: cause-to-effect, effect-to-cause, cause-to-effect with intervention, and effect-to-cause with intervention. This multi-dimensional evaluation method ensures that LLMs must exhibit a genuine understanding of causal structures by correctly answering questions across all four dimensions, mitigating the possibility of correct responses by chance. Furthermore, our benchmark explores the relationship between an LLM’s causal reasoning performance and its tendency to produce hallucinations. We present evaluations of state-of-the-art LLMs using our benchmark, providing valuable insights into their current causal reasoning capabilities across diverse domains. The dataset is publicly available for download at https://huggingface.co/datasets/CCLV/CausalBench

Hierarchical text classification (HTC) is a complex subtask under multi-label text classification, characterized by a hierarchical label taxonomy and data imbalance. The best-performing models aim to learn a static representation by combining document and hierarchical label information. However, the relevance of document sections can vary based on the hierarchy level, necessitating a dynamic document representation. To address this, we propose HiGen, a text-generation-based framework utilizing language models to encode dynamic text representations. We introduce a level-guided loss function to capture the relationship between text and label name semantics. Our approach incorporates a task-specific pretraining strategy, adapting the language model to in-domain knowledge and significantly enhancing performance for classes with limited examples. Furthermore, we present a new and valuable dataset called ENZYME, designed for HTC, which comprises articles from PubMed with the goal of predicting Enzyme Commission (EC) numbers. Through extensive experiments on the ENZYME dataset and the widely recognized WOS and NYT datasets, our methodology demonstrates superior performance, surpassing existing approaches while efficiently handling data and mitigating class imbalance. We release our code and dataset here: https://github.com/viditjain99/HiGen.

Language models increasingly rely on massive web crawls for diverse text data. However, these sources are rife with undesirable content. As such, resources like Wikipedia, books, and news often serve as anchors for automatically selecting web text most suitable for language modeling, a process typically referred to as quality filtering. Using a new dataset of U.S. high school newspaper articles—written by students from across the country—we investigate whose language is preferred by the quality filter used for GPT-3. We find that newspapers from larger schools, located in wealthier, educated, and urban zones (ZIP codes) are more likely to be classified as high quality. We also show that this quality measurement is unaligned with other sensible metrics, such as factuality or literary acclaim. We argue that privileging any corpus as high quality entails a language ideology, and more care is needed to construct training corpora for language models, with better transparency and justification for the inclusion or exclusion of various texts.

Access to mobile phones in many low- and middle-income countries has increased exponentially over the last 20 years, providing an opportunity to connect patients with healthcare interventions through mobile phones (known as mobile health). A barrier to large-scale implementation of interactive mobile health interventions is the human effort needed to manage participant messages. In this study, we explore the use of natural language processing to improve healthcare workers’ management of messages from pregnant and postpartum women in Kenya. Using multilingual, low-resource language text messages from the Mobile solutions for Women and Children’s health (Mobile WACh NEO) study, we developed models to assess urgency of incoming messages. We evaluated models using a novel approach that focuses on clinical usefulness in either triaging or prioritizing messages. Our best-performing models did not reach the threshold for clinical usefulness we set, but have the potential to improve nurse workflow and responsiveness to urgent messages.