Question answering (QA) and Machine Reading Comprehension (MRC) tasks have significantly advanced in recent years due to the rapid development of deep learning techniques and, more recently, large language models. At the same time, many benchmark datasets have become available for QA and MRC tasks. However, most existing large-scale benchmark datasets have been created predominantly using synchronous document collections like Wikipedia or the Web. Archival document collections, such as historical newspapers, contain valuable information from the past that is still not widely used to train large language models. To further contribute to advancing QA and MRC tasks and to overcome the limitation of previous datasets, we introduce ChroniclingAmericaQA, a large-scale temporal QA dataset with 487K question-answer pairs created based on the historical newspaper collection Chronicling America. Our dataset is constructed from a subset of the Chronicling America newspaper collection spanning 120 years. One of the significant challenges for utilizing digitized historical newspaper collections is the low quality of OCR text. Therefore, to enable realistic testing of QA models, our dataset can be used in three different ways: answering questions from raw and noisy content, answering questions from cleaner, corrected version of the content, as well as answering questions from scanned images of newspaper pages. This and the fact that ChroniclingAmericaQA spans the longest time period among available QA datasets make it quite a unique and useful resource.

If a person firmly believes in a non-factual statement, such as "The Earth is flat", and argues in its favor, there is no inherent intention to deceive. As the argumentation stems from genuine belief, it may be unlikely to exhibit the linguistic properties associated with deception or lying. This interplay of factuality, personal belief, and intent to deceive remains an understudied area. Disentangling the influence of these variables in argumentation is crucial to gain a better understanding of the linguistic properties attributed to each of them. To study the relation between deception and factuality, based on belief, we present the DeFaBel corpus, a crowd-sourced resource of belief-based deception. To create this corpus, we devise a study in which participants are instructed to write arguments supporting statements like "eating watermelon seeds can cause indigestion", regardless of its factual accuracy or their personal beliefs about the statement. In addition to the generation task, we ask them to disclose their belief about the statement. The collected instances are labelled as deceptive if the arguments are in contradiction to the participants' personal beliefs. Each instance in the corpus is thus annotated (or implicitly labelled) with personal beliefs of the author, factuality of the statement, and the intended deceptiveness. The DeFaBel corpus contains 1031 texts in German, out of which 643 are deceptive and 388 are non-deceptive. It is the first publicly available corpus for studying deception in German. In our analysis, we find that people are more confident in the persuasiveness of their arguments when the statement is aligned with their belief, but surprisingly less confident when they are generating arguments in favor of facts. The DeFaBel corpus can be obtained from https://www.ims.uni-stuttgart.de/data/defabel

In 2017, Rihanna posted a photo of herself on Instagram in which she appeared to have an extra thumb. It was, in retrospect, the thumb-shaped canary in the coal mine. Although far from the first celebrity "Photoshop fail," it just so happened to predict the era of faux-finger drama we now live in: AI image generators are universally, horrifically bad at rendering human hands. Today, an extra finger is a telltale sign of digital manipulation. Flaws aside, faking it has never been easier.

OpenAI, the company behind ChatGPT, is exploring whether users should be allowed to create artificial intelligence-generated pornography and other explicit content with its products. While the company stressed that its ban on deepfakes would continue to apply to adult material, campaigners suggested the proposal undermined its mission statement to produce "safe and beneficial" AI. OpenAI, which is also the developer of the DALL-E image generator, revealed it was considering letting developers and users "responsibly" create what it termed not-safe-for-work (NSFW) content through its products. OpenAI said this could include "erotica, extreme gore, slurs, and unsolicited profanity". It said: "We're exploring whether we can responsibly provide the ability to generate NSFW content in age-appropriate contexts … We look forward to better understanding user and societal expectations of model behaviour in this area."

Flamenco, recognized by UNESCO as part of the Intangible Cultural Heritage of Humanity, is a profound expression of cultural identity rooted in Andalusia, Spain. However, there is a lack of quantitative studies that help identify characteristic patterns in this long-lived music tradition. In this work, we present a computational analysis of Flamenco lyrics, employing natural language processing and machine learning to categorize over 2000 lyrics into their respective Flamenco genres, termed as $\textit{palos}$. Using a Multinomial Naive Bayes classifier, we find that lexical variation across styles enables to accurately identify distinct $\textit{palos}$. More importantly, from an automatic method of word usage, we obtain the semantic fields that characterize each style. Further, applying a metric that quantifies the inter-genre distance we perform a network analysis that sheds light on the relationship between Flamenco styles. Remarkably, our results suggest historical connections and $\textit{palo}$ evolutions. Overall, our work illuminates the intricate relationships and cultural significance embedded within Flamenco lyrics, complementing previous qualitative discussions with quantitative analyses and sparking new discussions on the origin and development of traditional music genres.

We evaluated 3 systems (ELIZA, GPT-3.5 and GPT-4) in a randomized, controlled, and preregistered Turing test. Human participants had a 5 minute conversation with either a human or an AI, and judged whether or not they thought their interlocutor was human. GPT-4 was judged to be a human 54% of the time, outperforming ELIZA (22%) but lagging behind actual humans (67%). The results provide the first robust empirical demonstration that any artificial system passes an interactive 2-player Turing test. The results have implications for debates around machine intelligence and, more urgently, suggest that deception by current AI systems may go undetected. Analysis of participants' strategies and reasoning suggests that stylistic and socio-emotional factors play a larger role in passing the Turing test than traditional notions of intelligence.

Many tasks related to Computational Social Science and Web Content Analysis involve classifying pieces of text based on the claims they contain. State-of-the-art approaches usually involve fine-tuning models on large annotated datasets, which are costly to produce. In light of this, we propose and release a qualitative and versatile few-shot learning methodology as a common paradigm for any claim-based textual classification task. This methodology involves defining the classes as arbitrarily sophisticated taxonomies of claims, and using Natural Language Inference models to obtain the textual entailment between these and a corpus of interest. The performance of these models is then boosted by annotating a minimal sample of data points, dynamically sampled using the well-established statistical heuristic of Probabilistic Bisection. We illustrate this methodology in the context of three tasks: climate change contrarianism detection, topic/stance classification and depression-relates symptoms detection.

Most modern recommendation algorithms are data-driven: they generate personalized recommendations by observing users' past behaviors. A common assumption in recommendation is that how a user interacts with a piece of content (e.g., whether they choose to "like" it) is a reflection of the content, but not of the algorithm that generated it. Although this assumption is convenient, it fails to capture user strategization: that users may attempt to shape their future recommendations by adapting their behavior to the recommendation algorithm. In this work, we test for user strategization by conducting a lab experiment and survey. To capture strategization, we adopt a model in which strategic users select their engagement behavior based not only on the content, but also on how their behavior affects downstream recommendations. Using a custom music player that we built, we study how users respond to different information about their recommendation algorithm as well as to different incentives about how their actions affect downstream outcomes. We find strong evidence of strategization across outcome metrics, including participants' dwell time and use of "likes." For example, participants who are told that the algorithm mainly pays attention to "likes" and "dislikes" use those functions 1.9x more than participants told that the algorithm mainly pays attention to dwell time. A close analysis of participant behavior (e.g., in response to our incentive conditions) rules out experimenter demand as the main driver of these trends. Further, in our post-experiment survey, nearly half of participants self-report strategizing "in the wild," with some stating that they ignore content they actually like to avoid over-recommendation of that content in the future. Together, our findings suggest that user strategization is common and that platforms cannot ignore the effect of their algorithms on user behavior.

Real-world graphs are complex to process for performing effective analysis, such as anomaly detection. However, recently, there have been several research efforts addressing the issues surrounding graph-based anomaly detection. In this paper, we discuss a comprehensive overview of anomaly detection techniques on graph data. We also discuss the various application domains which use those anomaly detection techniques. We present a new taxonomy that categorizes the different state-of-the-art anomaly detection methods based on assumptions and techniques. Within each category, we discuss the fundamental research ideas that have been done to improve anomaly detection. We further discuss the advantages and disadvantages of current anomaly detection techniques. Finally, we present potential future research directions in anomaly detection on graph-structured data.

Large language models (LLMs) are increasingly being introduced in workplace settings, with the goals of improving efficiency and fairness. However, concerns have arisen regarding these models' potential to reflect or exacerbate social biases and stereotypes. This study explores the potential impact of LLMs on hiring practices. To do so, we conduct an algorithm audit of race and gender biases in one commonly-used LLM, OpenAI's GPT-3.5, taking inspiration from the history of traditional offline resume audits. We conduct two studies using names with varied race and gender connotations: resume assessment (Study 1) and resume generation (Study 2). In Study 1, we ask GPT to score resumes with 32 different names (4 names for each combination of the 2 gender and 4 racial groups) and two anonymous options across 10 occupations and 3 evaluation tasks (overall rating, willingness to interview, and hireability). We find that the model reflects some biases based on stereotypes. In Study 2, we prompt GPT to create resumes (10 for each name) for fictitious job candidates. When generating resumes, GPT reveals underlying biases; women's resumes had occupations with less experience, while Asian and Hispanic resumes had immigrant markers, such as non-native English and non-U.S. education and work experiences. Our findings contribute to a growing body of literature on LLM biases, in particular when used in workplace contexts.