A scientist tests a continuous stream of hypotheses over time in the course of her investigation -- she does not test a predetermined, fixed number of hypotheses. The scientist wishes to make as many discoveries as possible while ensuring the number of false discoveries is controlled -- a well recognized way for accomplishing this is to control the false discovery rate (FDR). Prior methods for FDR control in the online setting have focused on formulating algorithms when specific dependency structures are assumed to exist between the test statistics of each hypothesis. However, in practice, these dependencies often cannot be known beforehand or tested after the fact. Our algorithm, e-LOND, provides FDR control under arbitrary, possibly unknown, dependence. We show that our method is more powerful than existing approaches to this problem through simulations. We also formulate extensions of this algorithm to utilize randomization for increased power, and for constructing confidence intervals in online selective inference.

We propose a general method to break down a main complex task into a set of intermediary easier sub-tasks, which are formulated in natural language as binary questions related to the final target task. Our method allows for representing each example by a vector consisting of the answers to these questions. We call this representation Natural Language Learned Features (NLLF). NLLF is generated by a small transformer language model (e.g., BERT) that has been trained in a Natural Language Inference (NLI) fashion, using weak labels automatically obtained from a Large Language Model (LLM). We show that the LLM normally struggles for the main task using in-context learning, but can handle these easiest subtasks and produce useful weak labels to train a BERT. The NLI-like training of the BERT allows for tackling zero-shot inference with any binary question, and not necessarily the ones seen during the training. We show that this NLLF vector not only helps to reach better performances by enhancing any classifier, but that it can be used as input of an easy-to-interpret machine learning model like a decision tree. This decision tree is interpretable but also reaches high performances, surpassing those of a pre-trained transformer in some cases.We have successfully applied this method to two completely different tasks: detecting incoherence in students' answers to open-ended mathematics exam questions, and screening abstracts for a systematic literature review of scientific papers on climate change and agroecology.

Offensive speech detection is a key component of content moderation. However, what is offensive can be highly subjective. This paper investigates how machine and human moderators disagree on what is offensive when it comes to real-world social web political discourse. We show that (1) there is extensive disagreement among the moderators (humans and machines); and (2) human and large-language-model classifiers are unable to predict how other human raters will respond, based on their political leanings. For (1), we conduct a noise audit at an unprecedented scale that combines both machine and human responses. For (2), we introduce a first-of-its-kind dataset of vicarious offense. Our noise audit reveals that moderation outcomes vary wildly across different machine moderators. Our experiments with human moderators suggest that political leanings combined with sensitive issues affect both first-person and vicarious offense. The dataset is available through https://github.com/Homan-Lab/voiced.

Despite the impressive performance of current AI models reported across various tasks, performance reports often do not include evaluations of how these models perform on the specific groups that will be impacted by these technologies. Among the minority groups under-represented in AI, data from low-income households are often overlooked in data collection and model evaluation. We evaluate the performance of a state-of-the-art vision-language model (CLIP) on a geo-diverse dataset containing household images associated with different income values (Dollar Street) and show that performance inequality exists among households of different income levels. Our results indicate that performance for the poorer groups is consistently lower than the wealthier groups across various topics and countries. We highlight insights that can help mitigate these issues and propose actionable steps for economic-level inclusive AI development. Code is available at https://github.com/MichiganNLP/Bridging_the_Digital_Divide.

Cyber attacks are often identified using system and network logs. There have been significant prior works that utilize provenance graphs and ML techniques to detect attacks, specifically advanced persistent threats, which are very difficult to detect. Lately, there have been studies where transformer-based language models are being used to detect various types of attacks from system logs. However, no such attempts have been made in the case of APTs. In addition, existing state-of-the-art techniques that use system provenance graphs, lack a data processing framework generalized across datasets for optimal performance. For mitigating this limitation as well as exploring the effectiveness of transformer-based language models, this paper proposes LogShield, a framework designed to detect APT attack patterns leveraging the power of self-attention in transformers. We incorporate customized embedding layers to effectively capture the context of event sequences derived from provenance graphs. While acknowledging the computational overhead associated with training transformer networks, our framework surpasses existing LSTM and Language models regarding APT detection. We integrated the model parameters and training procedure from the RoBERTa model and conducted extensive experiments on well-known APT datasets (DARPA OpTC and DARPA TC E3). Our framework achieved superior F1 scores of 98% and 95% on the two datasets respectively, surpassing the F1 scores of 96% and 94% obtained by LSTM models. Our findings suggest that LogShield's performance benefits from larger datasets and demonstrates its potential for generalization across diverse domains. These findings contribute to the advancement of APT attack detection methods and underscore the significance of transformer-based architectures in addressing security challenges in computer systems.

Deception and persuasion play a critical role in long-horizon dialogues between multiple parties, especially when the interests, goals, and motivations of the participants are not aligned. Such complex tasks pose challenges for current Large Language Models (LLM) as deception and persuasion can easily mislead them, especially in long-horizon multi-party dialogues. To this end, we explore the game of Avalon: The Resistance, a social deduction game in which players must determine each other's hidden identities to complete their team's objective. We introduce an online testbed and a dataset containing 20 carefully collected and labeled games among human players that exhibit long-horizon deception in a cooperative-competitive setting. We discuss the capabilities of LLMs to utilize deceptive long-horizon conversations between six human players to determine each player's goal and motivation. Particularly, we discuss the multimodal integration of the chat between the players and the game's state that grounds the conversation, providing further insights into the true player identities. We find that even current state-of-the-art LLMs do not reach human performance, making our dataset a compelling benchmark to investigate the decision-making and language-processing capabilities of LLMs. Our dataset and online testbed can be found at our project website: https://sstepput.github.io/Avalon-NLU/

Competency Questions (CQs) are a form of ontology functional requirements expressed as natural language questions. Inspecting CQs together with the axioms in an ontology provides critical insights into the intended scope and applicability of the ontology. CQs also underpin a number of tasks in the development of ontologies e.g. ontology reuse, ontology testing, requirement specification, and the definition of patterns that implement such requirements. Although CQs are integral to the majority of ontology engineering methodologies, the practice of publishing CQs alongside the ontological artefacts is not widely observed by the community. In this context, we present an experiment in retrofitting CQs from existing ontologies. We propose RETROFIT-CQs, a method to extract candidate CQs directly from ontologies using Generative AI. In the paper we present the pipeline that facilitates the extraction of CQs by leveraging Large Language Models (LLMs) and we discuss its application to a number of existing ontologies.

Human evaluation is often considered to be the gold standard method of evaluating a Natural Language Generation system. However, whilst its importance is accepted by the community at large, the quality of its execution is often brought into question. In this position paper, we argue that the generation of more esoteric forms of language - humour, irony and sarcasm - constitutes a subdomain where the characteristics of selected evaluator panels are of utmost importance, and every effort should be made to report demographic characteristics wherever possible, in the interest of transparency and replicability. We support these claims with an overview of each language form and an analysis of examples in terms of how their interpretation is affected by different participant variables. We additionally perform a critical survey of recent works in NLG to assess how well evaluation procedures are reported in this subdomain, and note a severe lack of open reporting of evaluator demographic information, and a significant reliance on crowdsourcing platforms for recruitment.

Cryogenic electron tomography (cryo-ET) is a technique for imaging biological samples such as viruses, cells, and proteins in 3D. A microscope collects a series of 2D projections of the sample, and the goal is to reconstruct the 3D density of the sample called the tomogram. This is difficult as the 2D projections have a missing wedge of information and are noisy. Tomograms reconstructed with conventional methods, such as filtered back-projection, suffer from the noise, and from artifacts and anisotropic resolution due to the missing wedge of information. To improve the visual quality and resolution of such tomograms, we propose a deep-learning approach for simultaneous denoising and missing wedge reconstruction called DeepDeWedge. DeepDeWedge is based on fitting a neural network to the 2D projections with a self-supervised loss inspired by noise2noise-like methods. The algorithm requires no training or ground truth data. Experiments on synthetic and real cryo-ET data show that DeepDeWedge achieves competitive performance for deep learning-based denoising and missing wedge reconstruction of cryo-ET tomograms.

Oral epithelial dysplasia (OED) is a premalignant histopathological diagnosis given to lesions of the oral cavity. OED grading is subject to large inter/intra-rater variability, resulting in the under/over-treatment of patients. We developed a new Transformer-based pipeline to improve detection and segmentation of OED in haematoxylin and eosin (H&E) stained whole slide images (WSIs). Our model was trained on OED cases (n = 260) and controls (n = 105) collected using three different scanners, and validated on test data from three external centres in the United Kingdom and Brazil (n = 78). Our internal experiments yield a mean F1-score of 0.81 for OED segmentation, which reduced slightly to 0.71 on external testing, showing good generalisability, and gaining state-of-the-art results. This is the first externally validated study to use Transformers for segmentation in precancerous histology images. Our publicly available model shows great promise to be the first step of a fully-integrated pipeline, allowing earlier and more efficient OED diagnosis, ultimately benefiting patient outcomes.