@INPROCEEDINGS{PAPUCCI_2026_INPROCEEDINGS_PVD_580421, 
 AUTHOR = {Papucci, M. and Venturi, G. and Dell'Orletta, F.}, 
 TITLE = {Controllable Sentence Simplification in Italian: Fine-Tuning Large Language Models on Automatically Generated Resources}, 
 YEAR = {2026}, 
 ABSTRACT = {This paper presents a study on readability-controlled Sentence Simplification for Italian, addressing the scarcity of annotated resources for low-resource languages. We introduce IMPaCTS (Italian Multilevel Parallel Corpus for Text Simplification), the first fully automatically created corpus of 1, 444, 160 original–simple sentence pairs automatically annotated with readability levels and linguistic features. It was generated using an Italian LLM prompted in zero-shot to produce multiple simplifications per input sentence. Increasing portions of the resource are used to fine-tune mono-and multilingual open-weight LLMs, conditioning them to generate simplifications at a target readability level. Results from automatic and human evaluations show that fine-tuning on IMPaCTS improves performance both in terms of task completion and adherence to the targeted readability levels compared to few-shot baselines}, 
 KEYWORDS = {Controlled Sentence Simplification, Readability Assessment, Large Language Models}, 
 PAGES = {7178-7191}, 
 URL = {http://www.lrec-conf.org/proceedings/lrec2026/pdf/2026.lrec2026-1.570}, 
 DOI = {10.63317/5fgm358dfxt5}, 
 ISBN = {978-2-493814-49-4}, 
 CONFERENCE_NAME = {15th Language Resources and Evaluation Conference (LREC 2026)}, 
 BOOKTITLE = {Proceedings of the 15th Language Resources and Evaluation Conference (LREC 2026)}, 
}

@INPROCEEDINGS{PAPUCCI_2026_INPROCEEDINGS_PVD_586463, 
 AUTHOR = {Papucci, M. and Venturi, G. and Dell'Orletta, F.}, 
 TITLE = {Lexical Conditioning of Model's Distribution through Uncertainty-gated Soft-Mixing of Probabilities}, 
 YEAR = {2026}, 
 ABSTRACT = {We present Uncertainty-Gated Lexical Decoding (UGLD), a decoding-time framework for fine-grained lexical control in Large Language Models (LLMs) that explicitly addresses the trade-off between controllability and fluency. UGLD adaptively scales intervention through an entropy-based gating mechanism derived from the model’s predictive distribution, activating control when uncertainty is high and limiting interference when predictions are confident. The method supports both promotion toward and against predefined vocabularies. We evaluate UGLD in Italian on two open-weight LLMs (ANITA 8B and Qwen 3 4B) across paraphrasing and free-text generation settings, considering Simple Vocabulary Conditioning and Jargon Reduction scenarios. Automatic evaluation shows consistent improvements in lexical coverage over standard decoding strategies, while human evaluation confirms that fluency is preserved under controlled intervention}, 
 KEYWORDS = {Controlled Text Generation, Lexically Constrained Decoding, Entropy-Gated Decoding}, 
 PAGES = {89-100}, 
 URL = {http://www.italianlp.it/wp-content/uploads/2026/05/papuccietalreadixtsar2026.pdf}, 
 ISBN = {978-2-493814-91-3}, 
 CONFERENCE_NAME = {Joint Workshop on Readability and Text Simplification (READIxTSAR)}, 
 BOOKTITLE = {Proceedings of the Joint Workshop on Readability and Text Simplification (READIxTSAR) @ LREC 2026}, 
}

@INPROCEEDINGS{PAPUCCI_2025_INPROCEEDINGS_PVD_570801, 
 AUTHOR = {Papucci, M. and Venturi, G. and Dell'Orletta, F.}, 
 TITLE = {Generating and Evaluating Multi-Level Text Simplification: A Case Study on Italian}, 
 YEAR = {2025}, 
 ABSTRACT = {Recent advances in Generative AI and Large Language Models (LLMs) have enabled the creation of highly realistic synthetic content, yet controlling model outputs remains a challenge. In this study, we explore the use of LLMs to generate high-quality synthetic data for Automatic Text Simplification (ATS), evaluating the ability of models fine-tuned on Italian to produce multiple simplified versions of the same original sentence that vary in readability and in their lexical and (morpho-)syntactic characteristics. The approach is tested across two domains, Wikipedia and Public Administration, allowing us to explore domain sensitivity. Additionally, we compare the linguistic phenomena observed in the generated data with those found in ATS resources previously created through manual or semi-automatic methods. Our results suggest that the best-performing LLM can generate linguistically diverse simplifications that align with known simplification patterns, offering a promising direction for building reliable ATS resources, including simplifications suited to varying levels of reader proficiency}, 
 KEYWORDS = {Automatic Text Simplification, Large Language Models, Synthetic Data, Linguistic Complexity, Sentence Readability}, 
 PAGES = {870-885}, 
 URL = {https://aclanthology.org/2025.clicit-1.82/}, 
 PUBLISHER = {CEUR Workshop Proceedings}, 
 ISBN = {979-12-243-0587-3}, 
 CONFERENCE_NAME = {Eleventh Italian Conference on Computational Linguistics (CLiC-it 2025)}, 
 BOOKTITLE = {Proceedings of the Eleventh Italian Conference on Computational Linguistics (CLiC-it 2025)}, 
}

@INPROCEEDINGS{PEDROTTI_2025_INPROCEEDINGS_PPCMPDE_554367, 
 AUTHOR = {Pedrotti, A. and Papucci, M. and Ciaccio, C. and Miaschi, A. and Puccetti, G. and Dell'Orletta, F. and Esuli, A.}, 
 TITLE = {Stress-testing machine generated text detection: shifting language models writing style to fool detectors}, 
 YEAR = {2025}, 
 ABSTRACT = {Recent advancements in Generative AI and Large Language Models (LLMs) have enabled the creation of highly realistic synthetic content, raising concerns about the potential for malicious use, such as misinformation and manipulation. Moreover, detecting Machine-Generated Text (MGT) remains challenging due to the lack of robust benchmarks that assess generalization to real-world scenarios. In this work, we evaluate the resilience of state-of-the-art MGT detectors (e. g., Mage, Radar, LLM-DetectAIve) to linguistically informed adversarial attacks. We develop a pipeline that fine-tunes language models using Direct Preference Optimization (DPO) to shift the MGT style toward human-written text (HWT), obtaining generations more challenging to detect by current models. Additionally, we analyze the linguistic shifts induced by the alignment and how detectors rely on “linguistic shortcuts” to detect texts. Our results show that detectors can be easily fooled with relatively few examples, resulting in a significant drop in detecting performances. This highlights the importance of improving detection methods and making them robust to unseen in-domain texts. We release code, models, and data to support future research on more robust MGT detection benchmarks}, 
 KEYWORDS = {machine-generated text detection, synthetic content detection}, 
 PAGES = {3010-3031}, 
 URL = {https://aclanthology.org/2025.findings-acl.156/}, 
 DOI = {10.18653/v1/2025.findings-acl.156}, 
 PUBLISHER = {Association for Computational Linguistics}, 
 ISBN = {979-8-89176-256-5}, 
 CONFERENCE_NAME = {NAACL 2025-Annual Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics. Findings}, 
 BOOKTITLE = {NAACL 2025 Findings proceedings}, 
}

@INPROCEEDINGS{MIASCHI_2023_INPROCEEDINGS_MPD_520527, 
 AUTHOR = {Miaschi, A. and Papucci, M. and Dell'Orletta, F.}, 
 TITLE = {Lost in Labels: An Ongoing Quest to Optimize Text-to-Text Label Selection for Classification}, 
 YEAR = {2023}, 
 ABSTRACT = {In this paper, we present an evaluation of the influence of label selection on the performance of a Sequence-to-Sequence Transformer model in a classification task. Our study investigates whether the choice of words used to represent classification categories affects the model’s performance, and if there exists a relationship between the model’s performance and the selected words. To achieve this, we fine-tuned an Italian T5 model on topic classification using various labels. Our results indicate that the different label choices can significantly impact the model’s performance. That being said, we did not find a clear answer on how these choices affect the model performances, highlighting the need for further research in optimizing label selection}, 
 KEYWORDS = {encoder-decoder, label selection, topic classification}, 
 URL = {https://iris.cnr.it/handle/20.500.14243/520527}, 
 VOLUME = {516 (394)}, 
 BOOKTITLE = {Proceedings of the 9th Italian Conference on Computational Linguistics CLiC-it 2023: Venice, Italy, November 30-December 2, 2023}, 
}

@INPROCEEDINGS{PAPUCCI_2022_INPROCEEDINGS_PDMD_415084, 
 AUTHOR = {Papucci, M. and De Nigris, C. and Miaschi, A. and Dell'Orletta, F.}, 
 TITLE = {Evaluating Text-To-Text Framework for Topic and Style Classification of Italian texts}, 
 YEAR = {2022}, 
 ABSTRACT = {In this paper, we propose an extensive evaluation of the first text-to-text Italian Neural Language Model (NLM), IT5 [1], on a classification scenario. In particular, we test the performance of IT5 on several tasks involving both the classification of the topic and the style of a set of Italian posts. We assess the model in two different configurations, single-and multi-task classification, and we compare it with a more traditional NLM based on the Transformer architecture (i. e. BERT). Moreover, we test its performance in a few-shot learning scenario. We also perform a qualitative investigation on the impact of label representations in modeling the classification of the IT5 model. Results show that IT5 could achieve good results, although generally lower than the BERT model. Nevertheless, we observe a significant performance improvement of the Text-to-text model in a multi-task classification scenario. Finally, we found that altering the representation of the labels mainly impacts the classification of the topic}, 
 KEYWORDS = {bert, style classification, t5, text-to-text, topic classification, transformers}, 
 PAGES = {56-70}, 
 URL = {http://www.scopus.com/record/display.url?eid=2-s2.0-85143252156\&origin=inward}, 
 VOLUME = {3287}, 
 CONFERENCE_NAME = {Sixth Workshop on Natural Language for Artificial Intelligence, NL4AI 2022}, 
}