Intimate Partner Violence refers to the abusive behaviours perpetrated on their own partner. Unfortunately this is a social issue that has witnessed an increase over time, particularly after Covid-19. IPV be circumscribed into two broad categories known as Intimate Partner Violence (IPV) and Cyber Intimate Partner Violence (C-IPV). Social Media and technologies can exacerbate these types of behaviors but some “digital footprints”, such as textual conversations, can be exploited by Artificial Intelligence models to detect and, in turn, prevent them. With this aim in mind, this paper describes a scenario in which the Italian Language Model family LLAmAntino can be exploited to explain the presence of toxicity elements in conversations related to teenage relationships and then educate the interlocutor to recognize these elements in the messages received.

With the rising interest in Large Language Models, deep architectures capable of solving a wide range of Natural LanguageGeneration tasks, an increasing number of open weights architectures have been developed and released online. In contrastwith older architectures, which were aimed at solving specific linguistic assignments, Large Language Models have shownoutstanding capabilities in solving several tasks at once, raising the question of whether they can truly comprehend naturallanguage. Nevertheless, evaluating this kind of capability is far from easy. One of the proposed solutions so far is usingbenchmarks that combine various types of tasks. This approach is based on the premise that achieving good performance ineach of these individual tasks can imply having developed a model capable of understanding language. However, while thisassumption is not incorrect, it is evident that it is not sufficient, and the evaluation of Large Language Models still remains anopen challenge. In this paper, we conduct a study aimed at highlighting the potential and limitations of current datasets andhow a new evaluation setting applied to language-adapted Large Language Models may provide more insight than traditionalapproaches.

Our work delves into the unexplored territory of Large-Language Models (LLMs) and their interactions with System Prompts, unveiling the previously undiscovered implications of SPLIT (System Prompt Induced Linguistic Transmutation) in commonly used state-of-the-art LLMs. Dissociative Identity Disorder, a complex and multifaceted mental health condition, is characterized by the presence of two or more distinct identities or personas within an individual, often with varying levels of awareness and control. The advent of large-language models has raised intriguing questions about the presence of such conditions in LLMs. Our research investigates the phenomenon of SPLIT, in which the System Prompt, a seemingly innocuous input, profoundly impacts the linguistic outputs of LLMs. The findings of our study reveal a striking correlation between the System Prompt and the emergence of distinct, persona-like linguistic patterns in the LLM’s responses. These patterns are not only reminiscent of the dissociative identities present in the original data but also exhibit a level of coherence and consistency that is uncommon in typical LLM outputs. As we continue to explore the capabilities of LLMs, it is imperative that we maintain a keen awareness of the potential for SPLIT and its significant implications for the development of more human-like and empathetic AI systems.

Dungeons & Dragons (D&D) is a classic tabletop game with a 50-year history. Its intricate and customizable gameplay allows players to create endless worlds and stories. Due to the highly narrative component of this game, D&D and many other interactive games represent a challenging setting for the Natural Language Generation (NLG) capabilities of LLMs. This paper explores using LLMs to generate new spells, which are one of the most captivating aspects of D&D gameplay. Due to the scarcity of resources available for such a specific task, we build a dataset of 3,259 instances by combining official and fan-made D&D spells. We considered several LLMs in generating spells, which underwent a quantitative and qualitative evaluation. Metrics including Bleu and BertScore were computed for quantitative assessments. Subsequently, we also conducted an in-vivo evaluation with a survey involving D&D players, which could assess the quality of the generated spells as well as their adherence to the rules. Furthermore, the paper emphasizes the open-sourcing of all models, datasets, and findings, aiming to catalyze further research on this topic.

The recent introduction of large-scale datasets for the WiC (Word in Context) task enables the creation of more reliable and meaningful contextualized word embeddings.However, most of the approaches to the WiC task use cross-encoders, which prevent the possibility of deriving comparable word embeddings.In this work, we introduce XL-LEXEME, a Lexical Semantic Change Detection model.XL-LEXEME extends SBERT, highlighting the target word in the sentence. We evaluate XL-LEXEME on the multilingual benchmarks for SemEval-2020 Task 1 - Lexical Semantic Change (LSC) Detection and the RuShiftEval shared task involving five languages: English, German, Swedish, Latin, and Russian.XL-LEXEME outperforms the state-of-the-art in English, German and Swedish with statistically significant differences from the baseline results and obtains state-of-the-art performance in the RuShiftEval shared task.

Sustainability reporting has become an annual requirement in many countries and for certain types of companies. Sustainability reports inform stakeholders about companies’ commitment to sustainable development and their economic, social, and environmental sustainability practices. However, the fact that norms and standards allow a certain discretion to be adopted by drafting organizations makes such reports hardly comparable in terms of layout, disclosures, key performance indicators (KPIs), and so on. In this work, we present a system based on natural language processing and information extraction techniques to retrieve relevant information from sustainability reports, compliant with the Global Reporting Initiative Standards, written in Italian and English language. Specifically, the system is able to identify references to the various sustainability topics discussed by the reports: on which page of the document those references have been found, the context of each reference, and if it is mentioned positively or negatively. The output of the system has been then evaluated against a ground truth obtained through a manual annotation process on 134 reports. Experimental outcomes highlight the affordability of the approach for improving sustainability disclosures, accessibility, and transparency, thus empowering stakeholders to conduct further analysis and considerations.

In this paper, we introduce the results of our submitted system to the FinTOC 2022 task. We address the task using a two-stage process: first, we detect titles using Document Image Analysis, then we train a supervised model for the hierarchical level prediction. We perform Document Image Analysis using a pre-trained Faster R-CNN on the PublyaNet dataset. We fine-tuned the model on the FinTOC 2022 training set. We extract orthographic and layout features from detected titles and use them to train a Random Forest model to predict the title level. The proposed system ranked #1 on both Title Detection and the Table of Content extraction tasks for Spanish. The system ranked #3 on both the two subtasks for English and French.

In the last few years, the increasing availability of large corpora spanning several time periods has opened new opportunities for the diachronic analysis of language. This type of analysis can bring to the light not only linguistic phenomena related to the shift of word meanings over time, but it can also be used to study the impact that societal and cultural trends have on this language change. This paper introduces a new resource for performing the diachronic analysis of named entities built upon Wikipedia page revisions. This resource enables the analysis over time of changes in the relations between entities (concepts), surface forms (words), and the contexts surrounding entities and surface forms, by analysing the whole history of Wikipedia internal links. We provide some useful use cases that prove the impact of this resource on diachronic studies and delineate some possible future usage.

Emotion detection from user-generated contents is growing in importance in the area of natural language processing. The approach we proposed for the EmoContext task is based on the combination of a CNN and an LSTM using a concatenation of word embeddings. A stack of convolutional neural networks (CNN) is used for capturing the hierarchical hidden relations among embedding features. Meanwhile, a long short-term memory network (LSTM) is used for capturing information shared among words of the sentence. Each conversation has been formalized as a list of word embeddings, in particular during experimental runs pre-trained Glove and Google word embeddings have been evaluated. Surface lexical features have been also considered, but they have been demonstrated to be not usefully for the classification in this specific task. The final system configuration achieved a micro F1 score of 0.7089. The python code of the system is fully available at https://github.com/marcopoli/EmoContext2019

The textual similarity is a crucial aspect for many extractive text summarization methods. A bag-of-words representation does not allow to grasp the semantic relationships between concepts when comparing strongly related sentences with no words in common. To overcome this issue, in this paper we propose a centroid-based method for text summarization that exploits the compositional capabilities of word embeddings. The evaluations on multi-document and multilingual datasets prove the effectiveness of the continuous vector representation of words compared to the bag-of-words model. Despite its simplicity, our method achieves good performance even in comparison to more complex deep learning models. Our method is unsupervised and it can be adopted in other summarization tasks.