We introduce IT5, the first family of encoder-decoder transformer models pretrained specifically on Italian. We document and perform a thorough cleaning procedure for a large Italian corpus and use it to pretrain four IT5 model sizes. We then introduce the ItaGen benchmark, which includes a broad range of natural language understanding and generation tasks for Italian, and use it to evaluate the performance of IT5 models and multilingual baselines. We find monolingual IT5 models to provide the best scale-to-performance ratio across tested models, consistently outperforming their multilingual counterparts and setting a new state-of-the-art for Italian language generation.

Recent availability of Large Language Models (LLMs) has led to the development of numerous LLM-based approaches aimed at providing natural language interfaces for various end-user tasks. These end-user tasks in turn can typically be accomplished by orchestrating a given set of APIs. In practice, natural language task requests (user queries) are often incomplete, i.e., they may not contain all the information required by the APIs. While LLMs excel at natural language processing (NLP) tasks, they frequently hallucinate on missing information or struggle with orchestrating the APIs. The key idea behind our proposed approach is to leverage logical reasoning and classical AI planning along with an LLM for accurately answering user queries including identification and gathering of any missing information in these queries. Our approach uses an LLM and ASP (Answer Set Programming) solver to translate a user query to a representation in Planning Domain Definition Language (PDDL) via an intermediate representation in ASP. We introduce a special API "get_info_api" for gathering missing information. We model all the APIs as PDDL actions in a way that supports dataflow between the APIs. Our approach then uses a classical AI planner to generate an orchestration of API calls (including calls to get_info_api) to answer the user query. Our evaluation results show that our approach significantly outperforms a pure LLM based approach by achieving over 95\% success rate in most cases on a dataset containing complete and incomplete single goal and multi-goal queries where the multi-goal queries may or may not require dataflow among the APIs.

During times of crisis, social media platforms play a vital role in facilitating communication and coordinating resources. Amidst chaos and uncertainty, communities often rely on these platforms to share urgent pleas for help, extend support, and organize relief efforts. However, the sheer volume of conversations during such periods, which can escalate to unprecedented levels, necessitates the automated identification and matching of requests and offers to streamline relief operations. This study addresses the challenge of efficiently identifying and matching assistance requests and offers on social media platforms during emergencies. We propose CReMa (Crisis Response Matcher), a systematic approach that integrates textual, temporal, and spatial features for multi-lingual request-offer matching. By leveraging CrisisTransformers, a set of pre-trained models specific to crises, and a cross-lingual embedding space, our methodology enhances the identification and matching tasks while outperforming strong baselines such as RoBERTa, MPNet, and BERTweet, in classification tasks, and Universal Sentence Encoder, Sentence Transformers in crisis embeddings generation tasks. We introduce a novel multi-lingual dataset that simulates scenarios of help-seeking and offering assistance on social media across the 16 most commonly used languages in Australia. We conduct comprehensive cross-lingual experiments across these 16 languages, also while examining trade-offs between multiple vector search strategies and accuracy. Additionally, we analyze a million-scale geotagged global dataset to comprehend patterns in relation to seeking help and offering assistance on social media. Overall, these contributions advance the field of crisis informatics and provide benchmarks for future research in the area.

People use language for various purposes. Apart from sharing information, individuals may use it to express emotions or to show respect for another person. In this paper, we focus on the formality level of machine-generated translations and present FAME-MT -- a dataset consisting of 11.2 million translations between 15 European source languages and 8 European target languages classified to formal and informal classes according to target sentence formality. This dataset can be used to fine-tune machine translation models to ensure a given formality level for each European target language considered. We describe the dataset creation procedure, the analysis of the dataset's quality showing that FAME-MT is a reliable source of language register information, and we present a publicly available proof-of-concept machine translation model that uses the dataset to steer the formality level of the translation. Currently, it is the largest dataset of formality annotations, with examples expressed in 112 European language pairs. The dataset is published online: https://github.com/laniqo-public/fame-mt/ .

Recent studies indicate that large multimodal models (LMMs) are highly robust against natural distribution shifts, often surpassing previous baselines. Despite this, domain-specific adaptation is still necessary, particularly in specialized areas like healthcare. Due to the impracticality of fine-tuning LMMs given their vast parameter space, this work investigates in-context learning (ICL) as an effective alternative for enhancing LMMs' adaptability. We find that the success of ICL heavily relies on the choice of demonstration, mirroring challenges seen in large language models but introducing unique complexities for LMMs facing distribution shifts. Our study addresses this by evaluating an unsupervised ICL method, TopKNearestPR, which selects in-context examples through a nearest example search based on feature similarity. We uncover that its effectiveness is limited by the deficiencies of pre-trained vision encoders under distribution shift scenarios. To address these challenges, we propose InvariantSelectPR, a novel method leveraging Class-conditioned Contrastive Invariance (CCI) for more robust demonstration selection. Specifically, CCI enhances pre-trained vision encoders by improving their discriminative capabilities across different classes and ensuring invariance to domain-specific variations. This enhancement allows the encoders to effectively identify and retrieve the most informative examples, which are then used to guide LMMs in adapting to new query samples under varying distributions. Our experiments show that InvariantSelectPR substantially improves the adaptability of LMMs, achieving significant performance gains on benchmark datasets, with a 34.2%$\uparrow$ accuracy increase in 7-shot on Camelyon17 and 16.9%$\uparrow$ increase in 7-shot on HAM10000 compared to the baseline zero-shot performance.

During the COVID-19 pandemic, the news media coverage encompassed a wide range of topics that includes viral transmission, allocation of medical resources, and government response measures. There have been studies on sentiment analysis of social media platforms during COVID-19 to understand the public response given the rise of cases and government strategies implemented to control the spread of the virus. Sentiment analysis can provide a better understanding of changes in societal opinions and emotional trends during the pandemic. Apart from social media, newspapers have played a vital role in the dissemination of information, including information from the government, experts, and also the public about various topics. A study of sentiment analysis of newspaper sources during COVID-19 for selected countries can give an overview of how the media covered the pandemic. In this study, we select The Guardian newspaper and provide a sentiment analysis during various stages of COVID-19 that includes initial transmission, lockdowns and vaccination. We employ novel large language models (LLMs) and refine them with expert-labelled sentiment analysis data. We also provide an analysis of sentiments experienced pre-pandemic for comparison. The results indicate that during the early pandemic stages, public sentiment prioritised urgent crisis response, later shifting focus to addressing the impact on health and the economy. In comparison with related studies about social media sentiment analyses, we found a discrepancy between The Guardian with dominance of negative sentiments (sad, annoyed, anxious and denial), suggesting that social media offers a more diversified emotional reflection. We found a grim narrative in The Guardian with overall dominance of negative sentiments, pre and during COVID-19 across news sections including Australia, UK, World News, and Opinion

Text classifiers are vulnerable to adversarial examples -- correctly-classified examples that are deliberately transformed to be misclassified while satisfying acceptability constraints. The conventional approach to finding adversarial examples is to define and solve a combinatorial optimisation problem over a space of allowable transformations. While effective, this approach is slow and limited by the choice of transformations. An alternate approach is to directly generate adversarial examples by fine-tuning a pre-trained language model, as is commonly done for other text-to-text tasks. This approach promises to be much quicker and more expressive, but is relatively unexplored. For this reason, in this work we train an encoder-decoder paraphrase model to generate a diverse range of adversarial examples. For training, we adopt a reinforcement learning algorithm and propose a constraint-enforcing reward that promotes the generation of valid adversarial examples. Experimental results over two text classification datasets show that our model has achieved a higher success rate than the original paraphrase model, and overall has proved more effective than other competitive attacks. Finally, we show how key design choices impact the generated examples and discuss the strengths and weaknesses of the proposed approach.

Integrating generative AI (GAI) into higher education is crucial for preparing a future generation of GAI-literate students. Yet a thorough understanding of the global institutional adoption policy remains absent, with most of the prior studies focused on the Global North and the promises and challenges of GAI, lacking a theoretical lens. This study utilizes the Diffusion of Innovations Theory to examine GAI adoption strategies in higher education across 40 universities from six global regions. It explores the characteristics of GAI innovation, including compatibility, trialability, and observability, and analyses the communication channels and roles and responsibilities outlined in university policies and guidelines. The findings reveal a proactive approach by universities towards GAI integration, emphasizing academic integrity, teaching and learning enhancement, and equity. Despite a cautious yet optimistic stance, a comprehensive policy framework is needed to evaluate the impacts of GAI integration and establish effective communication strategies that foster broader stakeholder engagement. The study highlights the importance of clear roles and responsibilities among faculty, students, and administrators for successful GAI integration, supporting a collaborative model for navigating the complexities of GAI in education. This study contributes insights for policymakers in crafting detailed strategies for its integration.

Modern named entity recognition systems have steadily improved performance in the age of larger and more powerful neural models. However, over the past several years, the state-of-the-art has seemingly hit another plateau on the benchmark CoNLL-03 English dataset. In this paper, we perform a deep dive into the test outputs of the highest-performing NER models, conducting a fine-grained evaluation of their performance by introducing new document-level annotations on the test set. We go beyond F1 scores by categorizing errors in order to interpret the true state of the art for NER and guide future work. We review previous attempts at correcting the various flaws of the test set and introduce CoNLL#, a new corrected version of the test set that addresses its systematic and most prevalent errors, allowing for low-noise, interpretable error analysis.

Financial market risk forecasting involves applying mathematical models, historical data analysis and statistical methods to estimate the impact of future market movements on investments. This process is crucial for investors to develop strategies, financial institutions to manage assets and regulators to formulate policy. In today's society, there are problems of high error rate and low precision in financial market risk prediction, which greatly affect the accuracy of financial market risk prediction. K-means algorithm in machine learning is an effective risk prediction technique for financial market. This study uses K-means algorithm to develop a financial market risk prediction system, which significantly improves the accuracy and efficiency of financial market risk prediction. Ultimately, the outcomes of the experiments confirm that the K-means algorithm operates with user-friendly simplicity and achieves a 94.61% accuracy rate