[{"id":241,"id_source":570501,"institutes":["ILC"],"type":"journal_article","type_order":1,"title":"Efficient multi-task learning with instance selection for biomedical NLP","year":2025,"authors":["Bonfigli, A.","Bacco, L.","Pecchia, L.","Merone, M.","Dell'Orletta, F."],"authors_source":"Bonfigli, A.; Bacco, L.; Pecchia, L.; Merone, M.; Dell'Orletta, F.","authors_cnr_name":["BONFIGLI, AGNESE","PECCHIA, LAURA","MERONE, MARIO","DELL'ORLETTA, FELICE"],"authors_cnr_id":["rp27321","rp21109","rp14221","rp22811"],"authors_cnr_institute":[],"abstract":"Background: Biomedical natural language processing (NLP) increasingly relies on large language models and extensive datasets, presenting significant computational challenges. Methods: We propose Blue5, a multi-task model based on SciFive that incorporates instance selection (IS) to enable efficient, multi-task learning (MTL) on biomedical data. We adapt the E2SC-IS framework for the biomedical domain, integrating a calibrated SVM classifier to reduce computational costs. Results: Our approach achieves an average data reduction of 26. 6% across the several tasks of the BLUE (Biomedical Language Understanding Evaluation) Benchmark, while maintaining performance comparable with state-of-the-art models. The multi-task SVM configuration emerges as the most effective, demonstrating the power of combining IS with MTL for biomedical NLP. As a result of the unified framework, Blue5 effectively selects the most informative instances across tasks, ensuring model generalization while efficiently handling multiple NLP tasks. Conclusion: Our work offers a practical solution to address growing computational demands, enabling more scalable and accessible applications of advanced NLP techniques in biomedical research and healthcare","keywords":["Biomedical NLP","BLUE benchmark","Computational efficiency","Instance selection","Multi-task learning"],"pages":"","url":"https:\/\/iris.cnr.it\/handle\/20.500.14243\/570501","volume":"190","doi":"10.1016\/j.compbiomed.2025.110050","editors":[],"editors_source":"","published":"COMPUTERS IN BIOLOGY AND MEDICINE","publisher":"","issn":"0010-4825","isbn":"","conference_name":"","conference_place":"","conference_date":"","last_updated_cnr":"2026-03-04 01:27:52","last_updated_oai":"2026-03-04 01:27:52","last_updated_www":"0000-00-00 00:00:00"},{"id":165,"id_source":570481,"institutes":["ILC"],"type":"journal_article","type_order":1,"title":"Cross-lingual distillation for domain knowledge transfer with sentence transformers","year":2025,"authors":["Piperno, R.","Bacco, L.","Dell'Orletta, F.","Merone, M.","Pecchia, L."],"authors_source":"Piperno, R.; Bacco, L.; Dell'Orletta, F.; Merone, M.; Pecchia, L.","authors_cnr_name":["Piperno, Ruben","DELL'ORLETTA, FELICE","MERONE, MARIO","PECCHIA, LAURA"],"authors_cnr_id":["rp26843","rp22811","rp14221","rp21109"],"authors_cnr_institute":[],"abstract":"Recent advancements in Natural Language Processing (NLP) have substantially enhanced language understanding. However, non-English languages, especially in specialized and low-resource domains like biomedicine, remain largely underrepresented. Bridging this gap is essential for promoting inclusivity and expanding the global applicability of NLP technologies. This study presents a cross-lingual knowledge distillation framework that utilizes sentence transformers to improve domain-specific NLP capabilities in non-English languages. Specifically, the framework focuses on biomedical text classification tasks. By aligning sentence embeddings between a teacher model trained on English biomedical corpora and a multilingual student model, the proposed method effectively transfers both domain-specific and task-specific knowledge. This alignment allows the student model to efficiently process and adapt to biomedical texts in Spanish, French, and German, particularly in low-resource settings with limited tuning data. Extensive experiments with domain-adapted models like BioBERT and multilingual BERT with machine-translated text pairs demonstrate substantial performance improvements in downstream biomedical NLP tasks. The proposed framework proves highly effective in scenarios characterized by limited training data availability. The results highlight the scalability and effectiveness of this approach, facilitating the development of robust multilingual models tailored to the biomedical domain, thus advancing global accessibility and impact in biomedical NLP applications","keywords":["Biomedical domain","Cross-lingual learning","Domain adaptation","Knowledge distillation","Sentence transformers"],"pages":"","url":"https:\/\/iris.cnr.it\/handle\/20.500.14243\/570481","volume":"311","doi":"10.1016\/j.knosys.2025.113079","editors":[],"editors_source":"","published":"KNOWLEDGE-BASED SYSTEMS","publisher":"","issn":"0950-7051","isbn":"","conference_name":"","conference_place":"","conference_date":"","last_updated_cnr":"2026-03-04 01:27:49","last_updated_oai":"2026-03-04 01:27:49","last_updated_www":"0000-00-00 00:00:00"},{"id":1664,"id_source":570763,"institutes":["ILC"],"type":"conference_article","type_order":7,"title":"A Novel Real-World Dataset of Italian Clinical Notes for NLP-based Decision Support in Low Back Pain Treatment","year":2025,"authors":["Bonfigli, A.","Piperno, R.","Bacco, L.","Dell'Orletta, F.","Brunato, D.","Crispino, F.","Papalia, G. F.","Russo, F.","Vadal\u00e0, G.","Papalia, R.","Merone, M.","Pecchia, L."],"authors_source":"Bonfigli, Agnese; Piperno, Ruben; Bacco, Luca; Dell'Orletta, Felice; Brunato, Dominique; Crispino, Filippo; Papalia, Giuseppe Francesco; Russo, Fabrizio; Vadal\u00e0, Gianluca; Papalia, Rocco; Merone, Mario; Pecchia, Leandro","authors_cnr_name":["BONFIGLI, AGNESE","Piperno, Ruben","DELL'ORLETTA, FELICE","BRUNATO, DOMINIQUE PIERINA","MERONE, MARIO"],"authors_cnr_id":["rp27321","rp26843","rp22811","rp06836","rp14221"],"authors_cnr_institute":[],"abstract":"Low back pain represents a leading source of disability worldwide and poses a significant challenge for evidence-based clinical decision support. In contexts where Italian-language resources for diversified therapeutic pathways are lacking, we have assembled a novel, annotated dataset comprising up to three pre-treatment documents per patient (MRI report, X-ray report, and patient visit notes), alongside demographic information (age and sex). The cohort consists of 176 patient records, stratified into three therapeutic groups: 50 conservative, 92 regenerative, and 34 surgical. The primary aim is to investigate whether the collected dataset can be harnessed to predict which of the three treatment modalities is most appropriate. To this end, six document-combination scenarios were defined, evaluating each single-report modality as well as all possible pairings. For each scenario, two modeling strategies were contrasted: a traditional Support Vector Machine classifier leveraging TF\u2013IDF features based on unigrams, bigrams, and trigrams, and a fine-tuned Italian BERT model adapted to our corpus. Experimental results indicate that classic n-gram\u2013based approaches achieve the highest performance (macro\u2013\ud835\udc391 up to 71. 3%). The BERT model, while outperforming the baseline, encounters limitations in this low-resource scenario. These findings suggest that the present dataset has the potential to catalyze the development of Italian-language clinical decision support systems that account for the distinct signatures of treatment pathways","keywords":["NLP in healthcare","Large Language Models (LLMs)","Italian Medical Corpus"],"pages":"","url":"https:\/\/iris.cnr.it\/handle\/20.500.14243\/570763","volume":"","doi":"","editors":[],"editors_source":"","published":"Proceedings of the Eleventh Italian Conference on Computational Linguistics (CLiC-it 2025)","publisher":"","issn":"","isbn":"","conference_name":"","conference_place":"","conference_date":"","last_updated_cnr":"2026-04-19 07:03:56","last_updated_oai":"2026-04-19 07:03:56","last_updated_www":"0000-00-00 00:00:00"},{"id":691,"id_source":570762,"institutes":["ILC"],"type":"conference_article","type_order":7,"title":"Doctor, Is That You? Evaluating Large Language Models on Italy\u2019s Medical School Entrance Exams","year":2025,"authors":["Piperno, R.","Bonfigli, A.","Dell'Orletta, F.","Pecchia, L.","Merone, M.","Bacco, L."],"authors_source":"Piperno, Ruben; Bonfigli, Agnese; Dell'Orletta, Felice; Pecchia, Leandro; Merone, Mario; Bacco, Luca","authors_cnr_name":["Piperno, Ruben","BONFIGLI, AGNESE","DELL'ORLETTA, FELICE","MERONE, MARIO"],"authors_cnr_id":["rp26843","rp27321","rp22811","rp14221"],"authors_cnr_institute":[],"abstract":"In recent years, Large Language Models (LLMs) have demonstrated remarkable capabilities across a variety of linguistic and cognitive tasks. This study investigates whether such models can succeed in one of Europe\u2019s most selective academic assessments: the Italian medical school entrance exam. We evaluate a wide selection of open-weights LLMs, ranging from natively Italian-pretrained models to multilingual and Italian-specialised variants, on a benchmark dataset comprising over 3, 300 real-world exam questions across five knowledge domains. Our experiments systematically explore the impact of language-specific pretraining, model size, prompt formulation and instruction tuning on exam performance. Results show that large multilingual models, particularly the Gemma-2-9B family, consistently outperform all other systems, surpassing the official admission threshold under all prompting settings. In contrast, models trained exclusively on Italian data fail to reach this threshold, even with larger architectures or instruction tuning. Additional analyses reveal that high-performing models display lower positional bias and greater inter-model consistency. These findings suggest that cross-domain reasoning and multilingual pretraining are key to handling multi-disciplinary educational tasks","keywords":["Large Language Models (LLMs)","Italian Medical Admission Test","NLP in healthcare"],"pages":"","url":"https:\/\/iris.cnr.it\/handle\/20.500.14243\/570762","volume":"","doi":"","editors":[],"editors_source":"","published":"Proceedings of the Eleventh Italian Conference on Computational Linguistics (CLiC-it 2025)","publisher":"","issn":"","isbn":"","conference_name":"","conference_place":"","conference_date":"","last_updated_cnr":"2026-03-04 01:28:06","last_updated_oai":"2026-03-04 01:28:06","last_updated_www":"0000-00-00 00:00:00"},{"id":1419,"id_source":518430,"institutes":["ILC"],"type":"journal_article","type_order":1,"title":"From pre-training to fine-tuning: An in-depth analysis of Large Language Models in the biomedical domain","year":2024,"authors":["Bonfigli, A.","Bacco, L.","Merone, M.","Dell'Orletta, F."],"authors_source":"Bonfigli, A.; Bacco, L.; Merone, M.; Dell'Orletta, F.","authors_cnr_name":["BONFIGLI, AGNESE","MERONE, MARIO","DELL'ORLETTA, FELICE"],"authors_cnr_id":["rp27321","rp14221","rp22811"],"authors_cnr_institute":[],"abstract":"In this study, we delve into the adaptation and effectiveness of Transformer-based, pre-trained Large Language Models (LLMs) within the biomedical domain, a field that poses unique challenges due to its complexity and the specialized nature of its data. Building on the foundation laid by the transformative architecture of Transformers, we investigate the nuanced dynamics of LLMs through a multifaceted lens, focusing on two domain-specific tasks, i. e., Natural Language Inference (NLI) and Named Entity Recognition (NER). Our objective is to bridge the knowledge gap regarding how these models\u2019 downstream performances correlate with their capacity to encapsulate task-relevant information. To achieve this goal, we probed and analyzed the inner encoding and attention mechanisms in LLMs, both encoder-and decoder-based, tailored for either general or biomedical-specific applications. This examination occurs before and after the models are fine-tuned across various data volumes. Our findings reveal that the models\u2019 downstream effectiveness is intricately linked to specific patterns within their internal mechanisms, shedding light on the nuanced ways in which LLMs process and apply knowledge in the biomedical context. The source code for this paper is available at https: \/\/github. com\/agnesebonfigli99\/LLMs-in-the-Biomedical-Domain","keywords":["Biomedical domain","Domain adaptation","Large Language Models"],"pages":"","url":"https:\/\/iris.cnr.it\/handle\/20.500.14243\/518430","volume":"157","doi":"10.1016\/j.artmed.2024.103003","editors":[],"editors_source":"","published":"ARTIFICIAL INTELLIGENCE IN MEDICINE","publisher":"","issn":"0933-3657","isbn":"","conference_name":"","conference_place":"","conference_date":"","last_updated_cnr":"2025-03-06 00:56:36","last_updated_oai":"2025-03-06 00:56:36","last_updated_www":"0000-00-00 00:00:00"},{"id":1645,"id_source":439016,"institutes":["ILC"],"type":"journal_article","type_order":1,"title":"A text style transfer system for reducing the physician-patient expertise gap: An analysis with automatic and human evaluations","year":2023,"authors":["Bacco, L.","Dell'Orletta, F.","Lai, H.","Merone, M.","Nissim, M."],"authors_source":"Bacco, Luca; Dell'Orletta, Felice; Lai, Huiyuan; Merone, Mario; Nissim, Malvina","authors_cnr_name":["DELL'ORLETTA, FELICE","MERONE, MARIO"],"authors_cnr_id":["rp22811","rp14221"],"authors_cnr_institute":[],"abstract":"Physicians and patients often come from different backgrounds and have varying levels of education, which can result in communication difficulties in the healthcare process. To address this expertise gap, we present a \"Text Style Transfer\" system. Our system uses Semantic Textual Similarity techniques based on Sentence Transformers models to create pseudo-parallel datasets from a large, non-parallel corpus of lay and expert texts. This approach allowed us to train a denoising autoencoder model (BART), overcoming the limitations of previous systems. Our extensive analysis, which includes both automatic metrics and human evaluations from both lay (patients) and expert (physicians) individuals, shows that our system outperforms state-of-the-art models and is comparable to human-provided gold references in some cases","keywords":["Natural language processing","Text style transfer","Text simplification"],"pages":"1-18","url":"https:\/\/www.sciencedirect.com\/science\/article\/pii\/S0957417423013763","volume":"233","doi":"10.1016\/j.eswa.2023.120874","editors":[],"editors_source":"","published":"EXPERT SYSTEMS WITH APPLICATIONS","publisher":"","issn":"0957-4174","isbn":"","conference_name":"","conference_place":"","conference_date":"","last_updated_cnr":"2025-04-25 00:27:54","last_updated_oai":"2025-04-25 00:27:54","last_updated_www":"0000-00-00 00:00:00"},{"id":1960,"id_source":446362,"institutes":["ILC"],"type":"journal_article","type_order":1,"title":"Natural language processing in low back pain and spine diseases: A systematic review","year":2022,"authors":["Bacco, L.","Russo, F.","Ambrosio, L.","D'Antoni, F.","Vollero, L.","Vadala, G.","Dell'Orletta, F.","Merone, M.","Papalia, R.","Denaro, V."],"authors_source":"Bacco, L; Russo, F; Ambrosio, L; D'Antoni, F; Vollero, L; Vadala, G; Dell'Orletta, F; Merone, M; Papalia, R; Denaro, V","authors_cnr_name":["DELL'ORLETTA, FELICE"],"authors_cnr_id":["rp22811"],"authors_cnr_institute":[],"abstract":"Natural Language Processing (NLP) is a discipline at the intersection between Computer Science (CS), Artificial Intelligence (AI), and Linguistics that leverages unstructured human-interpretable (natural) language text. In recent years, it gained momentum also in health-related applications and research. Although preliminary, studies concerning Low Back Pain (LBP) and other related spine disorders with relevant applications of NLP methodologies have been reported in the literature over the last few years. It motivated us to systematically review the literature comprised of two major public databases, PubMed and Scopus. To do so, we first formulated our research question following the PICO guidelines. Then, we followed a PRISMA-like protocol by performing a search query including terminologies of both technical (e. g., natural language and computational linguistics) and clinical (e. g., lumbar and spine surgery) domains. We collected 221 non-duplicated studies, 16 of which were eligible for our analysis. In this work, we present these studies divided into sub-categories, from both tasks and exploited models' points of view. Furthermore, we report a detailed description of techniques used to extract and process textual features and the several evaluation metrics used to assess the performance of the NLP models. However, what is clear from our analysis is that additional studies on larger datasets are needed to better define the role of NLP in the care of patients with spinal disorders","keywords":["natural language processing","Low Back Pain","Survey"],"pages":"","url":"http:\/\/www.scopus.com\/record\/display.url?eid=2-s2.0-85135163810&origin=inward","volume":"9","doi":"10.3389\/fsurg.2022.957085","editors":[],"editors_source":"","published":"FRONTIERS IN SURGERY","publisher":"","issn":"2296-875X","isbn":"","conference_name":"","conference_place":"","conference_date":"","last_updated_cnr":"2024-05-01 00:43:52","last_updated_oai":"2024-05-01 00:43:52","last_updated_www":"0000-00-00 00:00:00"},{"id":2006,"id_source":444101,"institutes":["ILC"],"type":"journal_article","type_order":1,"title":"Explainable sentiment analysis: A hierarchical transformer-based extractive summarization approach","year":2021,"authors":["Bacco, L.","Cimino, A.","Dell'Orletta, F.","Merone, M."],"authors_source":"Bacco L.; Cimino A.; Dell'orletta F.; Merone M.","authors_cnr_name":["DELL'ORLETTA, FELICE"],"authors_cnr_id":["rp22811"],"authors_cnr_institute":[],"abstract":"In recent years, the explainable artificial intelligence (XAI) paradigm is gaining wide research interest. The natural language processing (NLP) community is also approaching the shift of paradigm: building a suite of models that provide an explanation of the decision on some main task, without affecting the performances. It is not an easy job for sure, especially when very poorly interpretable models are involved, like the almost ubiquitous (at least in the NLP literature of the last years) transformers. Here, we propose two different transformer-based methodologies exploiting the inner hierarchy of the documents to perform a sentiment analysis task while extracting the most important (with regards to the model decision) sentences to build a summary as the explanation of the output. For the first architecture, we placed two transformers in cascade and leveraged the attention weights of the second one to build the summary. For the other architecture, we employed a single transformer to classify the single sentences in the document and then combine the probability scores of each to perform the classification and then build the summary. We compared the two methodologies by using the IMDB dataset, both in terms of classification and explainability performances. To assess the explainability part, we propose two kinds of metrics, based on benchmarking the models' summaries with human annotations. We recruited four independent operators to annotate few documents retrieved from the original dataset. Furthermore, we conducted an ablation study to highlight how implementing some strategies leads to important improvements on the explainability performance of the cascade transformers model","keywords":["Natural Language Processing","Sentiment Analysis","Explainable IA"],"pages":"","url":"http:\/\/www.scopus.com\/record\/display.url?eid=2-s2.0-85114289346&origin=inward","volume":"10","doi":"10.3390\/electronics10182195","editors":[],"editors_source":"","published":"ELECTRONICS","publisher":"","issn":"2079-9292","isbn":"","conference_name":"","conference_place":"","conference_date":"","last_updated_cnr":"2024-06-21 12:20:07","last_updated_oai":"2024-06-21 12:20:07","last_updated_www":"0000-00-00 00:00:00"},{"id":303,"id_source":401373,"institutes":["ILC"],"type":"conference_article","type_order":7,"title":"A Machine Learning approach for Sentiment Analysis for Italian Reviews in Healthcare","year":2020,"authors":["Bacco, L.","Cimino, A.","Paulon, L.","Merone, M.","Dell'Orletta, F."],"authors_source":"Bacco, L; Cimino, A; Paulon, L; Merone, M; Dell'Orletta, F","authors_cnr_name":["CIMINO, ANDREA","DELL'ORLETTA, FELICE"],"authors_cnr_id":["rp05770","rp22811"],"authors_cnr_institute":[],"abstract":"In this paper, we present our approach to the task of binary sentiment classification for Italian reviews in healthcare domain. We first collected a new dataset for such domain. Then, we compared the results obtained by two different systems, one including a Support Vector Machine and one with BERT. For the first one, we linguistic pre-processed the dataset to extract hand-crafted features exploited by the classifier. For the second one, we oversampled the dataset to achieve better results. Our results show that the SVM-based system, without the worry of having to oversample, has better performance than the BERT-based one, achieving anF1-score of 91. 21%","keywords":["natural language processing","sentiment analisys"],"pages":"","url":"https:\/\/iris.cnr.it\/handle\/20.500.14243\/401373","volume":"","doi":"","editors":[],"editors_source":"","published":"","publisher":"","issn":"","isbn":"","conference_name":"Seventh Italian Conference on Computational Linguistics (CLiC-it 2020)","conference_place":"","conference_date":"","last_updated_cnr":"2024-04-06 12:18:06","last_updated_oai":"2024-04-06 12:18:06","last_updated_www":"0000-00-00 00:00:00"}]