Andrea Bacciu

Andrea Bacciu, Giovanni Trappolini, Andrea Santilli et al.

This paper presents Fauno, the first and largest open-source Italian conversational Large Language Model (LLM). Our goal with Fauno is to democratize the study of LLMs in Italian, demonstrating that obtaining a fine-tuned conversational bot with a single GPU is possible. In addition, we release a collection of datasets for conversational AI in Italian. The datasets on which we fine-tuned Fauno include various topics such as general question answering, computer science, and medical questions. We release our code and datasets on \url{https://github.com/RSTLess-research/Fauno-Italian-LLM}

Filippo Betello, Antonio Purificato, Federico Siciliano et al.

Sequential Recommender Systems (SRSs) have emerged as a highly efficient approach to recommendation systems. By leveraging sequential data, SRSs can identify temporal patterns in user behaviour, significantly improving recommendation accuracy and relevance.Ensuring the reproducibility of these models is paramount for advancing research and facilitating comparisons between them. Existing works exhibit shortcomings in reproducibility and replicability of results, leading to inconsistent statements across papers. Our work fills these gaps by standardising data pre-processing and model implementations, providing a comprehensive code resource, including a framework for developing SRSs and establishing a foundation for consistent and reproducible experimentation. We conduct extensive experiments on several benchmark datasets, comparing various SRSs implemented in our resource. We challenge prevailing performance benchmarks, offering new insights into the SR domain. For instance, SASRec does not consistently outperform GRU4Rec. On the contrary, when the number of model parameters becomes substantial, SASRec starts to clearly dominate all the other SRSs. This discrepancy underscores the significant impact that experimental configuration has on the outcomes and the importance of setting it up to ensure precise and comprehensive results. Failure to do so can lead to significantly flawed conclusions, highlighting the need for rigorous experimental design and analysis in SRS research. Our code is available at https://github.com/antoniopurificato/recsys_repro_conf.

Andrea Bacciu, Florin Cuconasu, Federico Siciliano et al.

The emergence of large language models (LLMs) has revolutionized machine learning and related fields, showcasing remarkable abilities in comprehending, generating, and manipulating human language. However, their conventional usage through API-based text prompt submissions imposes certain limitations in terms of context constraints and external source availability. To address these challenges, we propose a novel framework called Reinforced Retrieval Augmented Machine Learning (RRAML). RRAML integrates the reasoning capabilities of LLMs with supporting information retrieved by a purpose-built retriever from a vast user-provided database. By leveraging recent advancements in reinforcement learning, our method effectively addresses several critical challenges. Firstly, it circumvents the need for accessing LLM gradients. Secondly, our method alleviates the burden of retraining LLMs for specific tasks, as it is often impractical or impossible due to restricted access to the model and the computational intensity involved. Additionally we seamlessly link the retriever's task with the reasoner, mitigating hallucinations and reducing irrelevant, and potentially damaging retrieved documents. We believe that the research agenda outlined in this paper has the potential to profoundly impact the field of AI, democratizing access to and utilization of LLMs for a wide range of entities.

Francesco Caso, Giovanni Trappolini, Andrea Bacciu et al.

Graph neural networks process information on graphs represented at a given resolution scale. We analyze the effect of using different coarse-grained graph resolutions, obtained through the Laplacian renormalization group theory, on node classification tasks. At the theory's core is grouping nodes connected by significant information flow at a given time scale. Representations of the graph at different scales encode interaction information at different ranges. We specifically experiment using representations at the characteristic scale of the graph's mesoscopic structures. We provide the models with the original graph and the graph represented at the characteristic resolution scale and compare them to models that can only access the original graph. Our results showed that models with access to both the original graph and the characteristic scale graph can achieve statistically significant improvements in test accuracy.

Antonio Purificato, Maria Sofia Bucarelli, Andrea Bacciu et al.

Human annotation cost and time remain significant bottlenecks in Natural Language Processing (NLP), with test data annotation being particularly expensive due to the stringent requirement for low-error and high-quality labels necessary for reliable model evaluation. Traditional approaches require annotating entire test sets, leading to substantial resource requirements. Active Testing is a framework that selects the most informative test samples for annotation. Given a labeling budget, it aims to choose the subset that best estimates model performance while minimizing cost and human effort. In this work, we formalize Active Testing in NLP and we conduct an extensive benchmarking of existing approaches across 18 datasets and 4 embedding strategies spanning 4 different NLP tasks. The experiments show annotation reductions of up to 95%, with performance estimation accuracy difference from the full test set within 1%. Our analysis reveals variations in method effectiveness across different data characteristics and task types, with no single approach emerging as universally superior. Lastly, to address the limitation of requiring a predefined annotation budget in existing sample selection strategies, we introduce an adaptive stopping criterion that automatically determines the optimal number of samples.

Andrea Bacciu, Marco Damonte, Marco Basaldella et al.

The majority of Neural Semantic Parsing (NSP) models are developed with the assumption that there are no concepts outside the ones such models can represent with their target symbols (closed-world assumption). This assumption leads to generate hallucinated outputs rather than admitting their lack of knowledge. Hallucinations can lead to wrong or potentially offensive responses to users. Hence, a mechanism to prevent this behavior is crucial to build trusted NSP-based Question Answering agents. To that end, we propose the Hallucination Simulation Framework (HSF), a general setting for stimulating and analyzing NSP model hallucinations. The framework can be applied to any NSP task with a closed-ontology. Using the proposed framework and KQA Pro as the benchmark dataset, we assess state-of-the-art techniques for hallucination detection. We then present a novel hallucination detection strategy that exploits the computational graph of the NSP model to detect the NSP hallucinations in the presence of ontology gaps, out-of-domain utterances, and to recognize NSP errors, improving the F1-Score respectively by ~21, ~24% and ~1%. This is the first work in closed-ontology NSP that addresses the problem of recognizing ontology gaps. We release our code and checkpoints at https://github.com/amazon-science/handling-ontology-gaps-in-semantic-parsing.

Nicola Cecere, Andrea Bacciu, Ignacio Fernández Tobías et al.

Uncertainty quantification (UQ) in Large Language Models (LLMs) is essential for their safe and reliable deployment, particularly in critical applications where incorrect outputs can have serious consequences. Current UQ methods typically rely on querying the model multiple times using non-zero temperature sampling to generate diverse outputs for uncertainty estimation. However, the impact of selecting a given temperature parameter is understudied, and our analysis reveals that temperature plays a fundamental role in the quality of uncertainty estimates. The conventional approach of identifying optimal temperature values requires expensive hyperparameter optimization (HPO) that must be repeated for each new model-dataset combination. We propose Monte Carlo Temperature (MCT), a robust sampling strategy that eliminates the need for temperature calibration. Our analysis reveals that: 1) MCT provides more robust uncertainty estimates across a wide range of temperatures, 2) MCT improves the performance of UQ methods by replacing fixed-temperature strategies that do not rely on HPO, and 3) MCT achieves statistical parity with oracle temperatures, which represent the ideal outcome of a well-tuned but computationally expensive HPO process. These findings demonstrate that effective UQ can be achieved without the computational burden of temperature parameter calibration.

Antonio Purificato, Maria Sofia Bucarelli, Anil Kumar Nelakanti et al.

Reliably labelling data typically requires annotations from multiple human workers. However, humans are far from being perfect. Hence, it is a common practice to aggregate labels gathered from multiple annotators to make a more confident estimate of the true label. Among many aggregation methods, the simple and well known Majority Vote (MV) selects the class label polling the highest number of votes. However, despite its importance, the optimality of MV's label aggregation has not been extensively studied. We address this gap in our work by characterising the conditions under which MV achieves the theoretically optimal lower bound on label estimation error. Our results capture the tolerable limits on annotation noise under which MV can optimally recover labels for a given class distribution. This certificate of optimality provides a more principled approach to model selection for label aggregation as an alternative to otherwise inefficient practices that sometimes include higher experts, gold labels, etc., that are all marred by the same human uncertainty despite huge time and monetary costs. Experiments on both synthetic and real world data corroborate our theoretical findings.

Andrea Alfarano, Alberto Alfarano, Linda Friso et al.

Spatio-Temporal predictive Learning is a self-supervised learning paradigm that enables models to identify spatial and temporal patterns by predicting future frames based on past frames. Traditional methods, which use recurrent neural networks to capture temporal patterns, have proven their effectiveness but come with high system complexity and computational demand. Convolutions could offer a more efficient alternative but are limited by their characteristic of treating all previous frames equally, resulting in poor temporal characterization, and by their local receptive field, limiting the capacity to capture distant correlations among frames. In this paper, we propose STLight, a novel method for spatio-temporal learning that relies solely on channel-wise and depth-wise convolutions as learnable layers. STLight overcomes the limitations of traditional convolutional approaches by rearranging spatial and temporal dimensions together, using a single convolution to mix both types of features into a comprehensive spatio-temporal patch representation. This representation is then processed in a purely convolutional framework, capable of focusing simultaneously on the interaction among near and distant patches, and subsequently allowing for efficient reconstruction of the predicted frames. Our architecture achieves state-of-the-art performance on STL benchmarks across different datasets and settings, while significantly improving computational efficiency in terms of parameters and computational FLOPs. The code is publicly available

Andrea Bacciu, Federico Siciliano, Nicola Tonellotto et al.

Sequential Recommender Systems (SRSs) are a popular type of recommender system that learns from a user's history to predict the next item they are likely to interact with. However, user interactions can be affected by noise stemming from account sharing, inconsistent preferences, or accidental clicks. To address this issue, we (i) propose a new evaluation protocol that takes multiple future items into account and (ii) introduce a novel relevance-aware loss function to train a SRS with multiple future items to make it more robust to noise. Our relevance-aware models obtain an improvement of ~1.2% of NDCG@10 and 0.88% in the traditional evaluation protocol, while in the new evaluation protocol, the improvement is ~1.63% of NDCG@10 and ~1.5% of HR w.r.t the best performing models.

Danilo Avola, Andrea Bacciu, Luigi Cinque et al.

Over the last year, the severe acute respiratory syndrome coronavirus-2 (SARS-CoV-2) and its variants have highlighted the importance of screening tools with high diagnostic accuracy for new illnesses such as COVID-19. To that regard, deep learning approaches have proven as effective solutions for pneumonia classification, especially when considering chest-x-rays images. However, this lung infection can also be caused by other viral, bacterial or fungi pathogens. Consequently, efforts are being poured toward distinguishing the infection source to help clinicians to diagnose the correct disease origin. Following this tendency, this study further explores the effectiveness of established neural network architectures on the pneumonia classification task through the transfer learning paradigm. To present a comprehensive comparison, 12 well-known ImageNet pre-trained models were fine-tuned and used to discriminate among chest-x-rays of healthy people, and those showing pneumonia symptoms derived from either a viral (i.e., generic or SARS-CoV-2) or bacterial source. Furthermore, since a common public collection distinguishing between such categories is currently not available, two distinct datasets of chest-x-rays images, describing the aforementioned sources, were combined and employed to evaluate the various architectures. The experiments were performed using a total of 6330 images split between train, validation and test sets. For all models, common classification metrics were computed (e.g., precision, f1-score) and most architectures obtained significant performances, reaching, among the others, up to 84.46% average f1-score when discriminating the 4 identified classes. Moreover, confusion matrices and activation maps computed via the Grad-CAM algorithm were also reported to present an informed discussion on the networks classifications.