While large language models (LLMs) have proven to be effective on a large variety of tasks, they are also known to hallucinate information. To measure whether an LLM prefers factually consistent continuations of its input, we propose a new benchmark called FIB(Factual Inconsistency Benchmark) that focuses on the task of summarization. Specifically, our benchmark involves comparing the scores an LLM assigns to a factually consistent versus a factually inconsistent summary for an input news article. For factually consistent summaries, we use human-written reference summaries that we manually verify as factually consistent. To generate summaries that are factually inconsistent, we generate summaries from a suite of summarization models that we have manually annotated as factually inconsistent. A model's factual consistency is then measured according to its accuracy, i.e.\ the proportion of documents where it assigns a higher score to the factually consistent summary. To validate the usefulness of FIB, we evaluate 23 large language models ranging from 1B to 176B parameters from six different model families including BLOOM and OPT. We find that existing LLMs generally assign a higher score to factually consistent summaries than to factually inconsistent summaries. However, if the factually inconsistent summaries occur verbatim in the document, then LLMs assign a higher score to these factually inconsistent summaries than factually consistent summaries. We validate design choices in our benchmark including the scoring method and source of distractor summaries. Our code and benchmark data can be found at https://github.com/r-three/fib.

Robots can be very useful to automate tasks and reduce the human effort required. But for the robot to know, how to perform tasks, we need to give it a clear set of steps to follow. It is nearly impossible to provide a robot with instructions for every possible task. Therefore we have a Universal Functional object-oriented network (FOON) which was created and expanded and has a lot of existing recipe information [1]. But certain tasks are complicated for robots to perform and similarly, some tasks are complicated for humans to perform. Therefore weights have been added to functional units to represent the chance of successful execution of the motion by the robot [2]. Given a set of kitchen items and a goal node, using Universal FOON, a robot must be able to determine if the required items are present in the kitchen, and if yes, get the steps to convert the required kitchen items to the goal node. Now through this paper, we use two algorithms (IDS and GBFS) to retrieve a task tree (if possible) for a goal node and a given set of kitchen items. The following would be the different parts of the paper: Section II FOON creation, where we will discuss the different terminologies related to FOON and visualization of FOON. In Section III Methodology we discuss the IDS and GBFS search algorithms and the two different heuristics implemented and used in GBFS. In Section IV Experiment/Discussion, we compare the performance of different algorithms. In the final section V, we specify the references of the papers that have been cited.

Fake news on social media has large, negative implications for society. However, little is known about what linguistic cues make people fall for fake news and, hence, how to design effective countermeasures for social media. In this study, we seek to understand which linguistic cues make people fall for fake news. Linguistic cues (e.g., adverbs, personal pronouns, positive emotion words, negative emotion words) are important characteristics of any text and also affect how people process real vs. fake news. Specifically, we compare the role of linguistic cues across both cognitive processing (related to careful thinking) and affective processing (related to unconscious automatic evaluations). To this end, we performed a within-subject experiment where we collected neurophysiological measurements of 42 subjects while these read a sample of 40 real and fake news articles. During our experiment, we measured cognitive processing through eye fixations, and affective processing in situ through heart rate variability. We find that users engage more in cognitive processing for longer fake news articles, while affective processing is more pronounced for fake news written in analytic words. To the best of our knowledge, this is the first work studying the role of linguistic cues in fake news processing. Altogether, our findings have important implications for designing online platforms that encourage users to engage in careful thinking and thus prevent them from falling for fake news.

Developing aerial robots that can both safely navigate and execute assigned mission without any human intervention - i.e., fully autonomous aerial mobility of passengers and goods - is the larger vision that guides the research, design, and development efforts in the aerial autonomy space. However, it is highly challenging to concurrently operationalize all types of aerial vehicles that are operating fully autonomously sharing the airspace. Full autonomy of the aerial transportation sector includes several aspects, such as design of the technology that powers the vehicles, operations of multi-agent fleets, and process of certification that meets stringent safety requirements of aviation sector. Thereby, Autonomous Advanced Aerial Mobility is still a vague term and its consequences for researchers and professionals are ambiguous. To address this gap, we present a comprehensive perspective on the emerging field of autonomous advanced aerial mobility, which involves the use of unmanned aerial vehicles (UAVs) and electric vertical takeoff and landing (eVTOL) aircraft for various applications, such as urban air mobility, package delivery, and surveillance. The article proposes a scalable and extensible autonomy framework consisting of four main blocks: sensing, perception, planning, and controls. Furthermore, the article discusses the challenges and opportunities in multi-agent fleet operations and management, as well as the testing, validation, and certification aspects of autonomous aerial systems. Finally, the article explores the potential of monolithic models for aerial autonomy and analyzes their advantages and limitations. The perspective aims to provide a holistic picture of the autonomous advanced aerial mobility field and its future directions.

COVID-19 has created a major public health problem worldwide and other problems such as economic crisis, unemployment, mental distress, etc. The pandemic is deadly in the world and involves many people not only with infection but also with problems, stress, wonder, fear, resentment, and hatred. Twitter is a highly influential social media platform and a significant source of health-related information, news, opinion and public sentiment where information is shared by both citizens and government sources. Therefore an effective analysis of COVID-19 tweets is essential for policymakers to make wise decisions. However, it is challenging to identify interesting and useful content from major streams of text to understand people's feelings about the important topics of the COVID-19 tweets. In this paper, we propose a new \textit{framework} for analyzing topic-based sentiments by extracting key topics with significant labels and classifying positive, negative, or neutral tweets on each topic to quickly find common topics of public opinion and COVID-19-related attitudes. While building our model, we take into account hybridization of BiLSTM and GRU structures for sentiment analysis to achieve our goal. The experimental results show that our topic identification method extracts better topic labels and the sentiment analysis approach using our proposed hybrid deep learning model achieves the highest accuracy compared to traditional models.

Designing high-quality educational questions is a challenging and time-consuming task. In this work, we propose a novel approach that utilizes prompt-based techniques to generate descriptive and reasoning-based questions. However, current question-answering (QA) datasets are inadequate for conducting our experiments on prompt-based question generation (QG) in an educational setting. Therefore, we curate a new QG dataset called EduProbe for school-level subjects, by leveraging the rich content of NCERT textbooks. We carefully annotate this dataset as quadruples of 1) Context: a segment upon which the question is formed; 2) Long Prompt: a long textual cue for the question (i.e., a longer sequence of words or phrases, covering the main theme of the context); 3) Short Prompt: a short textual cue for the question (i.e., a condensed representation of the key information or focus of the context); 4) Question: a deep question that aligns with the context and is coherent with the prompts. We investigate several prompt-based QG methods by fine-tuning pre-trained transformer-based large language models (LLMs), namely PEGASUS, T5, MBART, and BART. Moreover, we explore the performance of two general-purpose pre-trained LLMs such as Text-Davinci-003 and GPT-3.5-Turbo without any further training. By performing automatic evaluation, we show that T5 (with long prompt) outperforms all other models, but still falls short of the human baseline. Under human evaluation criteria, TextDavinci-003 usually shows better results than other models under various prompt settings. Even in the case of human evaluation criteria, QG models mostly fall short of the human baseline. Our code and dataset are available at: https://github.com/my625/PromptQG

Graph neural networks (GNNs) have led to major breakthroughs in a variety of domains such as drug discovery, social network analysis, and travel time estimation. However, they lack interpretability which hinders human trust and thereby deployment to settings with high-stakes decisions. A line of interpretable methods approach this by discovering a small set of relevant concepts as subgraphs in the last GNN layer that together explain the prediction. This can yield oversimplified explanations, failing to explain the interaction between GNN layers. To address this oversight, we provide HELP (Hierarchical Explainable Latent Pooling), a novel, inherently interpretable graph pooling approach that reveals how concepts from different GNN layers compose to new ones in later steps. HELP is more than 1-WL expressive and is the first non-spectral, end-to-end-learnable, hierarchical graph pooling method that can learn to pool a variable number of arbitrary connected components. We empirically demonstrate that it performs on-par with standard GCNs and popular pooling methods in terms of accuracy while yielding explanations that are aligned with expert knowledge in the domains of chemistry and social networks. In addition to a qualitative analysis, we employ concept completeness scores as well as concept conformity, a novel metric to measure the noise in discovered concepts, quantitatively verifying that the discovered concepts are significantly easier to fully understand than those from previous work. Our work represents a first step towards an understanding of graph neural networks that goes beyond a set of concepts from the final layer and instead explains the complex interplay of concepts on different levels.

The customization of recommended content to users holds significant importance in enhancing user experiences across a wide spectrum of applications such as e-commerce, music, and shopping. Graph-based methods have achieved considerable performance by capturing user-item interactions. However, these methods tend to utilize randomly constructed embeddings in the dataset used for training the recommender, which lacks any user preferences. Here, we propose the concept of variational embeddings as a means of pre-training the recommender system to improve the feature propagation through the layers of graph convolutional networks (GCNs). The graph variational embedding collaborative filtering (GVECF) is introduced as a novel framework to incorporate representations learned through a variational graph auto-encoder which are embedded into a GCN-based collaborative filtering. This approach effectively transforms latent high-order user-item interactions into more trainable vectors, ultimately resulting in better performance in terms of recall and normalized discounted cumulative gain(NDCG) metrics. The experiments conducted on benchmark datasets demonstrate that our proposed method achieves up to 13.78% improvement in the recall over the test data.

Synthetic text plays a vital role in data augmentation, model robustness, privacy preservation and scenario analysis. It is usually formulated as conditional text generation where a given source document is transformed using substitutions, paraphrasing, back translation, mixups etc. [1] to obtain a modified document. We argue that conditioning on the unstructured text limits the ability to mix text fragments coherently and produces transformations that are not confined to essential information, a critical necessity for long-form text. Furthermore, explaining the generated text becomes challenging, particularly detecting hallucinations [2]. We propose here a decompose and expand technique to generate synthetic text, where the semantic frames [3] of a source document are first extracted, and this compact interim form is used to generate the transformed text.

Self-supervised learning (SSL) is a powerful technique for learning robust representations from unlabeled data. By learning to remain invariant to applied data augmentations, methods such as SimCLR and MoCo are able to reach quality on par with supervised approaches. However, this invariance may be harmful to solving some downstream tasks which depend on traits affected by augmentations used during pretraining, such as color. In this paper, we propose to foster sensitivity to such characteristics in the representation space by modifying the projector network, a common component of self-supervised architectures. Specifically, we supplement the projector with information about augmentations applied to images. In order for the projector to take advantage of this auxiliary conditioning when solving the SSL task, the feature extractor learns to preserve the augmentation information in its representations. Our approach, coined Conditional Augmentation-aware Self-supervised Learning (CASSLE), is directly applicable to typical joint-embedding SSL methods regardless of their objective functions. Moreover, it does not require major changes in the network architecture or prior knowledge of downstream tasks. In addition to an analysis of sensitivity towards different data augmentations, we conduct a series of experiments, which show that CASSLE improves over various SSL methods, reaching state-of-the-art performance in multiple downstream tasks.