We present ARGUS, an end-to-end Argument Mining (AM) tool that exploits Large Language Models (LLMs) to automatically perform all core AM tasks, i.e., Argument Component Segmentation, Classification, Relation Identification, and Relation Classification. Furthermore, ARGUS builds the corresponding argumentation framework (AF) and seamlessly integrates symbolic solvers to compute extensions and perform formal reasoning. ARGUS is designed to ensure broad flexibility and usability, supporting any open-source or commercial LLMs and symbolic solvers, providing a ready-to-use platform for exploring neuro-symbolic approaches to argumentation in both research and practical applications.

As Large Language Models (LLMs) have reached human-like fluency and coherence, distinguishing machine-generated text (MGT) from human-written content becomes increasingly difficult.While early efforts in MGT detection have focused on binary classification, the growing landscape and diversity of LLMs require a more fine-grained yet challenging authorship attribution (AA), i.e., being able to identify the precise generator (LLM or human) behind a text.However, AA remains nowadays confined to a monolingual setting, with English being the most investigated one, overlooking the multilingual nature and usage of modern LLMs.In this work, we introduce the problem of Multilingual Authorship Attribution, which involves attributing texts to human or multiple LLM generators across diverse languages.Focusing on 18 languages-covering multiple families and writing scripts-and 8 generators (7 LLMs and the human-authored class), we investigate the multilingual suitability of monolingual AA methods in terms of their crosslingual transferability, and the impact of generators on attribution performance.Our results reveal that while certain monolingual AA methods can be adapted to multilingual settings, significant limitations and challenges remain, particularly in transferring across diverse language families, underscoring the complexity of multilingual AA and the need for more robust approaches to better match real-world scenarios.

The rapid growth of Non-Fungible Tokens (NFTs) and the extensive trading activities associated with such an intriguing domain led to the emergence of large-scale and interconnected transaction networks involving the most prominent NFT markets. Despite such interdependencies representing an inestimable source of information for the proper understanding of the NFT landscape, previous studies treated each market separately, overlooking relevant phenomena. In this study, we explore a multilayer network modeling approach to analyze transactions in multiple NFT markets. We reveal previously unnoticed macroscopic and mesoscopic traits by investigating indicators that discern whether markets are independent or linked: users trading NFTs are organized in cross-market communities where multi-market users act as bridges across marketplaces, adapting to the diverse nature of the markets they operate in. We also conduct an in-depth examination of such multi-market users, studying their specific activity patterns that leave a distinctive mark on the system: the majority of multi-market users well differentiate their earnings and expenses among the markets, while a fraction of them is directed toward a more polarized money allocation based on the typology of the markets. By offering a fresh perspective on this intricate financial system and emphasizing the importance of perceiving the NFT markets as a unique and interconnected world, our study paves the way for further contributions aimed at unraveling the complexity of cryptosystems and understanding the latent phenomena across NFT markets.

Link prediction algorithms for multilayer networks are in principle required to effectively account for the entire layered structure while capturing the unique contexts offered by each layer. However, many existing approaches excel at predicting specific links in certain layers but struggle with others, as they fail to effectively leverage the diverse information encoded across different network layers. In this paper, we present MoE-ML-LP , the first Mixture-of-Experts (MoE) framework specifically designed for multilayer link prediction. Building on top of multilayer heuristics for link prediction, MoE-ML-LP synthesizes the decisions taken by diverse experts, resulting in significantly enhanced predictive capabilities. Our extensive experimental evaluation on real-world and synthetic networks demonstrates that MoE-ML-LP consistently outperforms several baselines and competing methods, achieving remarkable improvements of +60% in Mean Reciprocal Rank, +82% in Hits@1, +55% in Hits@5, and +41% in Hits@10. Furthermore, MoE-ML-LP features a modular architecture that enables the seamless integration of newly developed experts without necessitating the re-training of the entire framework, fostering efficiency and scalability to new experts, paving the way for future advancements in link prediction.

The emergence of unveiling human-like behaviors in Large Language Models (LLMs) has led to a closer connection between NLP and human psychology. However, research on the personalities exhibited by LLMs has largely been confined to limited investigations using individual psychological tests, primarily focusing on a small number of commercially licensed LLMs. This approach overlooks the extensive use and significant advancements observed in open-source LLMs. This work aims to address both the above limitations by conducting an in-depth investigation of a significant body of 12 LLM Agents based on the most representative Open models, through the two most well-known psychological assessment tests, namely Myers-Briggs Type Indicator (MBTI) and Big Five Inventory (BFI). Our approach involves evaluating the intrinsic personality traits of LLM agents and determining the extent to which these agents can mimic human personalities when conditioned by specific personalities and roles. Our findings unveil that (i) each LLM agent showcases distinct human personalities; (ii) personality-conditioned prompting produces varying effects on the agents, with only few successfully mirroring the imposed personality, while most of them being ``closed-minded'' (i.e., they retain their intrinsic traits); and (iii) combining role and personality conditioning can enhance the agents' ability to mimic human personalities. Our work represents a step up in understanding the dense relationship between NLP and human psychology through the lens of LLMs.

Morality serves as the foundation of societal structure, guiding legal systems, shaping cultural values, and influencing individual self-perception. With the rise and pervasiveness of generative AI tools, and particularly Large Language Models (LLMs), concerns arise regarding how these tools capture and potentially alter moral dimensions through machine-generated text manipulation. Based on the Moral Foundation Theory, our work investigates this topic by analyzing the behavior of 12 LLMs among the most widely used Open and uncensored (i.e., ”abliterated”) models, and leveraging human-annotated datasets used in moral-related analysis. Results have shown varying levels of alteration of moral expressions depending on the type of text modification task and moral-related conditioning prompt.

We present PersonaGen, a novel dataset for investigating persona-driven machine-generated text (MGT) produced by Open Large Language Models (OLLMS). PersonaGen is specifically designed to investigate how synthetic persona profiles affect, guide, or manifest in MGT. We built PersonaGen by pairing curated persona-profiles (i.e., description of characteristics, background, and goals) across eight thematic domains (e.g., Physics, Education, Medicine) with prompts covering various narrative or opinion-style content (e.g., stories, commonsense). Open-ended generations were produced by six representative OLLMs, yielding a total of 1.44 million persona-driven generations. PersonaGen supports multiple research tasks, such as machine-generated text attribution, persona category detection, and persona profile identification, thus providing a valuable resource for studying LLM controllability and role-playing behavior, as well as the impact of persona profile conditioning in downstream tasks. We have released PersonaGen on the Hugging Face platform at https://doi.org/10.57967/hf/5805.

Open Large Language Models (OLLMs) are increasingly leveraged in generative AI applications, posing new challenges for detecting their outputs.We propose OpenTuringBench, a new benchmark based on OLLMs, designed to train and evaluate machine-generated text detectors on the Turing Test and Authorship Attribution problems.OpenTuringBench focuses on a representative set of OLLMs, and features a number of challenging evaluation tasks, including human/machine-manipulated texts, outof-domain texts, and texts from previously unseen models.We also provide OTBDetector, a contrastive learning framework to detect and attribute OLLM-based machine-generated texts.Results highlight the relevance and varying degrees of difficulty of the OpenTuringBench tasks, with our detector achieving remarkable capabilities across the various tasks and outperforming most existing detectors.

The fervor for Non-Fungible Tokens (NFTs) attracted countless creators, leading to a Big Bang of digital assets driven by latent or explicit forms of inspiration, as in many creative processes. This work exploits Vision Transformers and graph-based modeling to delve into visual inspiration phenomena between NFTs over the years, i.e., the visual influence that can be detected whenever an NFT appears to be visually close to another that was published earlier in the market. Our goals include unveiling the main structural traits that shape visual inspiration networks, exploring the interrelation between visual inspiration and asset performances, investigating crypto influence on inspiration processes, and explaining the inspiration relationships among NFTs. Our findings unveil how the pervasiveness of inspiration led to a temporary saturation of the visual feature space, the impact of the dichotomy between inspiring and inspired NFTs on their financial performance, and an intrinsic self-regulatory mechanism between markets and inspiration waves. Our work can serve as a starting point for gaining a broader view of the evolution of Web3.

The significant progress in the development of Large Language Models has contributed to blurring the distinction between human and AI-generated text. The increasing pervasiveness of AI-generated text and the difficulty in detecting it poses new challenges for our society. In this paper, we tackle the problem of detecting and attributing AI-generated text by proposing WhosAI, a triplet-network contrastive learning framework designed to predict whether a given input text has been generated by humans or AI and to unveil the authorship of the text. Unlike most existing approaches, our proposed framework is conceived to learn semantic similarity representations from multiple generators at once, thus equally handling both detection and attribution tasks. Furthermore, WhosAI is model-agnostic and scalable to the release of new AI text-generation models by incorporating their generated instances into the embedding space learned by our framework. Experimental results on the TuringBench benchmark of 200K news articles show that our proposed framework achieves outstanding results in both the Turing Test and Authorship Attribution tasks, outperforming all the methods listed in the TuringBench benchmark leaderboards.

In this work, we present SONAR, a web-based tool for multimodal exploration of Non-Fungible Token (NFT) inspiration networks. SONAR is conceived to support both creators and traders in the emerging Web3 by providing an interactive visualization of the inspiration-driven connections between NFTs, at both individual level and collection level. SONAR can hence be useful to identify new investment opportunities as well as anomalous inspirations. To demonstrate SONAR's capabilities, we present an application to the largest and most representative dataset concerning the NFT landscape to date, showing how our proposed tool can scale and ensure high-level user experience up to millions of edges.

Non-Fungible Tokens (NFTs) represent deeds of ownership, based on blockchain technologies and smart contracts, of unique crypto assets on digital art forms (e.g., artworks or collectibles). In the spotlight after skyrocketing in 2021, NFTs have attracted the attention of crypto enthusiasts and investors intent on placing promising investments in this profitable market. However, the NFT financial performance prediction has not been widely explored to date.

We present LawNet-Viz, a web-based tool for the modeling, analysis and visualization of law reference networks extracted from a statute law corpus. LawNet-Viz is designed to support legal research tasks and help legal professionals as well as laymen visually exploring the article connections built upon the explicit law references detected in the article contents. To demonstrate LawNet-Viz, we show its application to the Italian Civil Code (ICC), which exploits a recent BERT-based model fine-tuned on the ICC. LawNet-Viz is a system prototype that is planned for product development.